diff --git a/bin/fetch-ai-models.js b/bin/fetch-ai-models.js index 9cedee887b8d760..2fac8a7b475014d 100644 --- a/bin/fetch-ai-models.js +++ b/bin/fetch-ai-models.js @@ -1,14 +1,24 @@ -import fs from "fs"; - -fetch("https://ai-cloudflare-com.pages.dev/api/models") - .then((res) => res.json()) - .then((data) => { - data.models.map((model) => { - const fileName = model.name.split("/")[2]; - fs.writeFileSync( - `./src/content/workers-ai-models/${fileName}.json`, - JSON.stringify(model, null, 4), - "utf-8", - ); - }); - }); +import fs from "node:fs"; +import path from "node:path"; + +const OUTPUT_DIR = path.join(process.cwd(), "src/content/workers-ai-models"); + +const response = await fetch("https://ai-cloudflare-com.pages.dev/api/models"); +const data = await response.json(); +const existingFiles = new Set( + fs.readdirSync(OUTPUT_DIR).filter((file) => file.endsWith(".json")), +); + +for (const model of data.models) { + const fileName = `${model.name.split("/")[2]}.json`; + existingFiles.delete(fileName); + fs.writeFileSync( + path.join(OUTPUT_DIR, fileName), + JSON.stringify(model, null, 4), + "utf-8", + ); +} + +for (const fileName of existingFiles) { + fs.unlinkSync(path.join(OUTPUT_DIR, fileName)); +} diff --git a/bin/fetch-catalog-models.ts b/bin/fetch-catalog-models.ts index 76ca70ba77e33ee..9d643b62c10bf7c 100644 --- a/bin/fetch-catalog-models.ts +++ b/bin/fetch-catalog-models.ts @@ -91,6 +91,22 @@ const API_BASE_URL = const PER_PAGE = 100; const CONCURRENCY = 5; +function getPlannedDeprecationDate(model: CatalogModel): string | undefined { + const metadata = model.metadata as Record | undefined; + const value = metadata?.planned_deprecation_date; + return typeof value === "string" ? value : undefined; +} + +function isDeprecated(model: CatalogModel): boolean { + const plannedDeprecationDate = getPlannedDeprecationDate(model); + if (!plannedDeprecationDate) { + return false; + } + + const timestamp = new Date(plannedDeprecationDate).getTime(); + return !Number.isNaN(timestamp) && Date.now() > timestamp; +} + function parseArgs(): { file?: string } { const args = process.argv.slice(2); const fileIndex = args.indexOf("--file"); @@ -125,11 +141,19 @@ async function loadFromFile(filePath: string): Promise { } const publicModels = models.filter((m) => !m.private); - const skipped = models.length - publicModels.length; + const activeModels = publicModels.filter((m) => !isDeprecated(m)); + const skippedPrivate = models.length - publicModels.length; + const skippedDeprecated = publicModels.length - activeModels.length; + const skippedNotes = [ + skippedPrivate > 0 ? `${skippedPrivate} private skipped` : null, + skippedDeprecated > 0 ? `${skippedDeprecated} deprecated skipped` : null, + ] + .filter(Boolean) + .join(", "); console.log( - ` Loaded ${models.length} models${skipped > 0 ? ` (${skipped} private skipped)` : ""}`, + ` Loaded ${models.length} models${skippedNotes ? ` (${skippedNotes})` : ""}`, ); - return publicModels; + return activeModels; } function getApiHeaders(token: string): Record { @@ -373,6 +397,7 @@ function writeModels(models: CatalogModel[]): void { // Write each model to a JSON file let written = 0; const skipped: string[] = []; + const skippedDeprecated: string[] = []; for (const model of models) { // Skip private models @@ -381,6 +406,11 @@ function writeModels(models: CatalogModel[]): void { continue; } + if (isDeprecated(model)) { + skippedDeprecated.push(model.model_id); + continue; + } + // Trim string fields that may have leading/trailing whitespace model.name = model.name.trim(); model.description = model.description.trim(); @@ -408,6 +438,9 @@ function writeModels(models: CatalogModel[]): void { if (skipped.length > 0) { console.log(` Skipped (private): ${skipped.length}`); } + if (skippedDeprecated.length > 0) { + console.log(` Skipped (deprecated): ${skippedDeprecated.length}`); + } console.log(` Output: ${OUTPUT_DIR}`); } diff --git a/src/content/workers-ai-models/deepseek-coder-6.7b-base-awq.json b/src/content/workers-ai-models/deepseek-coder-6.7b-base-awq.json deleted file mode 100644 index a204b0d54b54991..000000000000000 --- a/src/content/workers-ai-models/deepseek-coder-6.7b-base-awq.json +++ /dev/null @@ -1,466 +0,0 @@ -{ - "id": "7f180530-2e16-4116-9d26-f49fbed9d372", - "source": 2, - "name": "@hf/thebloke/deepseek-coder-6.7b-base-awq", - "description": "Deepseek Coder is composed of a series of code language models, each trained from scratch on 2T tokens, with a composition of 87% code and 13% natural language in both English and Chinese.", - "task": { - "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", - "name": "Text Generation", - "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." - }, - "created_at": "2024-02-06 18:16:27.183", - "tags": [], - "properties": [ - { - "property_id": "beta", - "value": "true" - }, - { - "property_id": "context_window", - "value": "4096" - }, - { - "property_id": "planned_deprecation_date", - "value": "2025-10-01" - }, - { - "property_id": "terms", - "value": "https://huggingface.co/TheBloke/deepseek-coder-6.7B-base-AWQ" - } - ], - "schema": { - "input": { - "type": "object", - "oneOf": [ - { - "title": "Prompt", - "properties": { - "prompt": { - "type": "string", - "minLength": 1, - "description": "The input text prompt for the model to generate a response." - }, - "lora": { - "type": "string", - "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." - }, - "response_format": { - "title": "JSON Mode", - "type": "object", - "properties": { - "type": { - "type": "string", - "enum": [ - "json_object", - "json_schema" - ] - }, - "json_schema": {} - } - }, - "raw": { - "type": "boolean", - "default": false, - "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." - }, - "stream": { - "type": "boolean", - "default": false, - "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." - }, - "max_tokens": { - "type": "integer", - "default": 256, - "description": "The maximum number of tokens to generate in the response." - }, - "temperature": { - "type": "number", - "default": 0.6, - "minimum": 0, - "maximum": 5, - "description": "Controls the randomness of the output; higher values produce more random results." - }, - "top_p": { - "type": "number", - "minimum": 0.001, - "maximum": 1, - "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." - }, - "top_k": { - "type": "integer", - "minimum": 1, - "maximum": 50, - "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." - }, - "seed": { - "type": "integer", - "minimum": 1, - "maximum": 9999999999, - "description": "Random seed for reproducibility of the generation." - }, - "repetition_penalty": { - "type": "number", - "minimum": 0, - "maximum": 2, - "description": "Penalty for repeated tokens; higher values discourage repetition." - }, - "frequency_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Decreases the likelihood of the model repeating the same lines verbatim." - }, - "presence_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Increases the likelihood of the model introducing new topics." - } - }, - "required": [ - "prompt" - ] - }, - { - "title": "Messages", - "properties": { - "messages": { - "type": "array", - "description": "An array of message objects representing the conversation history.", - "items": { - "type": "object", - "properties": { - "role": { - "type": "string", - "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." - }, - "content": { - "oneOf": [ - { - "type": "string", - "description": "The content of the message as a string." - }, - { - "type": "array", - "description": "Array of text content parts.", - "items": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "Type of the content (text)" - }, - "text": { - "type": "string", - "description": "Text content" - } - } - } - } - ] - } - }, - "required": [ - "role", - "content" - ] - } - }, - "functions": { - "type": "array", - "items": { - "type": "object", - "properties": { - "name": { - "type": "string" - }, - "code": { - "type": "string" - } - }, - "required": [ - "name", - "code" - ] - } - }, - "tools": { - "type": "array", - "description": "A list of tools available for the assistant to use.", - "items": { - "type": "object", - "oneOf": [ - { - "properties": { - "name": { - "type": "string", - "description": "The name of the tool. More descriptive the better." - }, - "description": { - "type": "string", - "description": "A brief description of what the tool does." - }, - "parameters": { - "type": "object", - "description": "Schema defining the parameters accepted by the tool.", - "properties": { - "type": { - "type": "string", - "description": "The type of the parameters object (usually 'object')." - }, - "required": { - "type": "array", - "description": "List of required parameter names.", - "items": { - "type": "string" - } - }, - "properties": { - "type": "object", - "description": "Definitions of each parameter.", - "additionalProperties": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "The data type of the parameter." - }, - "description": { - "type": "string", - "description": "A description of the expected parameter." - } - }, - "required": [ - "type", - "description" - ] - } - } - }, - "required": [ - "type", - "properties" - ] - } - }, - "required": [ - "name", - "description", - "parameters" - ] - }, - { - "properties": { - "type": { - "type": "string", - "description": "Specifies the type of tool (e.g., 'function')." - }, - "function": { - "type": "object", - "description": "Details of the function tool.", - "properties": { - "name": { - "type": "string", - "description": "The name of the function." - }, - "description": { - "type": "string", - "description": "A brief description of what the function does." - }, - "parameters": { - "type": "object", - "description": "Schema defining the parameters accepted by the function.", - "properties": { - "type": { - "type": "string", - "description": "The type of the parameters object (usually 'object')." - }, - "required": { - "type": "array", - "description": "List of required parameter names.", - "items": { - "type": "string" - } - }, - "properties": { - "type": "object", - "description": "Definitions of each parameter.", - "additionalProperties": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "The data type of the parameter." - }, - "description": { - "type": "string", - "description": "A description of the expected parameter." - } - }, - "required": [ - "type", - "description" - ] - } - } - }, - "required": [ - "type", - "properties" - ] - } - }, - "required": [ - "name", - "description", - "parameters" - ] - } - }, - "required": [ - "type", - "function" - ] - } - ] - } - }, - "response_format": { - "title": "JSON Mode", - "type": "object", - "properties": { - "type": { - "type": "string", - "enum": [ - "json_object", - "json_schema" - ] - }, - "json_schema": {} - } - }, - "raw": { - "type": "boolean", - "default": false, - "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." - }, - "stream": { - "type": "boolean", - "default": false, - "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." - }, - "max_tokens": { - "type": "integer", - "default": 256, - "description": "The maximum number of tokens to generate in the response." - }, - "temperature": { - "type": "number", - "default": 0.6, - "minimum": 0, - "maximum": 5, - "description": "Controls the randomness of the output; higher values produce more random results." - }, - "top_p": { - "type": "number", - "minimum": 0.001, - "maximum": 1, - "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." - }, - "top_k": { - "type": "integer", - "minimum": 1, - "maximum": 50, - "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." - }, - "seed": { - "type": "integer", - "minimum": 1, - "maximum": 9999999999, - "description": "Random seed for reproducibility of the generation." - }, - "repetition_penalty": { - "type": "number", - "minimum": 0, - "maximum": 2, - "description": "Penalty for repeated tokens; higher values discourage repetition." - }, - "frequency_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Decreases the likelihood of the model repeating the same lines verbatim." - }, - "presence_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Increases the likelihood of the model introducing new topics." - } - }, - "required": [ - "messages" - ] - } - ] - }, - "output": { - "oneOf": [ - { - "type": "object", - "properties": { - "response": { - "type": "string", - "description": "The generated text response from the model" - }, - "usage": { - "type": "object", - "description": "Usage statistics for the inference request", - "properties": { - "prompt_tokens": { - "type": "number", - "description": "Total number of tokens in input", - "default": 0 - }, - "completion_tokens": { - "type": "number", - "description": "Total number of tokens in output", - "default": 0 - }, - "total_tokens": { - "type": "number", - "description": "Total number of input and output tokens", - "default": 0 - } - } - }, - "tool_calls": { - "type": "array", - "description": "An array of tool calls requests made during the response generation", - "items": { - "type": "object", - "properties": { - "arguments": { - "type": "object", - "description": "The arguments passed to be passed to the tool call request" - }, - "name": { - "type": "string", - "description": "The name of the tool to be called" - } - } - } - } - }, - "required": [ - "response" - ] - }, - { - "type": "string", - "format": "binary" - } - ] - } - } -} \ No newline at end of file diff --git a/src/content/workers-ai-models/deepseek-coder-6.7b-instruct-awq.json b/src/content/workers-ai-models/deepseek-coder-6.7b-instruct-awq.json deleted file mode 100644 index 9faa3b5a0a1c065..000000000000000 --- a/src/content/workers-ai-models/deepseek-coder-6.7b-instruct-awq.json +++ /dev/null @@ -1,466 +0,0 @@ -{ - "id": "60474554-f03b-4ff4-8ecc-c1b7c71d7b29", - "source": 2, - "name": "@hf/thebloke/deepseek-coder-6.7b-instruct-awq", - "description": "Deepseek Coder is composed of a series of code language models, each trained from scratch on 2T tokens, with a composition of 87% code and 13% natural language in both English and Chinese.", - "task": { - "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", - "name": "Text Generation", - "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." - }, - "created_at": "2024-02-06 18:18:27.462", - "tags": [], - "properties": [ - { - "property_id": "beta", - "value": "true" - }, - { - "property_id": "context_window", - "value": "4096" - }, - { - "property_id": "planned_deprecation_date", - "value": "2025-10-01" - }, - { - "property_id": "terms", - "value": "https://huggingface.co/TheBloke/deepseek-coder-6.7B-instruct-AWQ" - } - ], - "schema": { - "input": { - "type": "object", - "oneOf": [ - { - "title": "Prompt", - "properties": { - "prompt": { - "type": "string", - "minLength": 1, - "description": "The input text prompt for the model to generate a response." - }, - "lora": { - "type": "string", - "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." - }, - "response_format": { - "title": "JSON Mode", - "type": "object", - "properties": { - "type": { - "type": "string", - "enum": [ - "json_object", - "json_schema" - ] - }, - "json_schema": {} - } - }, - "raw": { - "type": "boolean", - "default": false, - "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." - }, - "stream": { - "type": "boolean", - "default": false, - "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." - }, - "max_tokens": { - "type": "integer", - "default": 256, - "description": "The maximum number of tokens to generate in the response." - }, - "temperature": { - "type": "number", - "default": 0.6, - "minimum": 0, - "maximum": 5, - "description": "Controls the randomness of the output; higher values produce more random results." - }, - "top_p": { - "type": "number", - "minimum": 0.001, - "maximum": 1, - "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." - }, - "top_k": { - "type": "integer", - "minimum": 1, - "maximum": 50, - "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." - }, - "seed": { - "type": "integer", - "minimum": 1, - "maximum": 9999999999, - "description": "Random seed for reproducibility of the generation." - }, - "repetition_penalty": { - "type": "number", - "minimum": 0, - "maximum": 2, - "description": "Penalty for repeated tokens; higher values discourage repetition." - }, - "frequency_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Decreases the likelihood of the model repeating the same lines verbatim." - }, - "presence_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Increases the likelihood of the model introducing new topics." - } - }, - "required": [ - "prompt" - ] - }, - { - "title": "Messages", - "properties": { - "messages": { - "type": "array", - "description": "An array of message objects representing the conversation history.", - "items": { - "type": "object", - "properties": { - "role": { - "type": "string", - "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." - }, - "content": { - "oneOf": [ - { - "type": "string", - "description": "The content of the message as a string." - }, - { - "type": "array", - "description": "Array of text content parts.", - "items": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "Type of the content (text)" - }, - "text": { - "type": "string", - "description": "Text content" - } - } - } - } - ] - } - }, - "required": [ - "role", - "content" - ] - } - }, - "functions": { - "type": "array", - "items": { - "type": "object", - "properties": { - "name": { - "type": "string" - }, - "code": { - "type": "string" - } - }, - "required": [ - "name", - "code" - ] - } - }, - "tools": { - "type": "array", - "description": "A list of tools available for the assistant to use.", - "items": { - "type": "object", - "oneOf": [ - { - "properties": { - "name": { - "type": "string", - "description": "The name of the tool. More descriptive the better." - }, - "description": { - "type": "string", - "description": "A brief description of what the tool does." - }, - "parameters": { - "type": "object", - "description": "Schema defining the parameters accepted by the tool.", - "properties": { - "type": { - "type": "string", - "description": "The type of the parameters object (usually 'object')." - }, - "required": { - "type": "array", - "description": "List of required parameter names.", - "items": { - "type": "string" - } - }, - "properties": { - "type": "object", - "description": "Definitions of each parameter.", - "additionalProperties": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "The data type of the parameter." - }, - "description": { - "type": "string", - "description": "A description of the expected parameter." - } - }, - "required": [ - "type", - "description" - ] - } - } - }, - "required": [ - "type", - "properties" - ] - } - }, - "required": [ - "name", - "description", - "parameters" - ] - }, - { - "properties": { - "type": { - "type": "string", - "description": "Specifies the type of tool (e.g., 'function')." - }, - "function": { - "type": "object", - "description": "Details of the function tool.", - "properties": { - "name": { - "type": "string", - "description": "The name of the function." - }, - "description": { - "type": "string", - "description": "A brief description of what the function does." - }, - "parameters": { - "type": "object", - "description": "Schema defining the parameters accepted by the function.", - "properties": { - "type": { - "type": "string", - "description": "The type of the parameters object (usually 'object')." - }, - "required": { - "type": "array", - "description": "List of required parameter names.", - "items": { - "type": "string" - } - }, - "properties": { - "type": "object", - "description": "Definitions of each parameter.", - "additionalProperties": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "The data type of the parameter." - }, - "description": { - "type": "string", - "description": "A description of the expected parameter." - } - }, - "required": [ - "type", - "description" - ] - } - } - }, - "required": [ - "type", - "properties" - ] - } - }, - "required": [ - "name", - "description", - "parameters" - ] - } - }, - "required": [ - "type", - "function" - ] - } - ] - } - }, - "response_format": { - "title": "JSON Mode", - "type": "object", - "properties": { - "type": { - "type": "string", - "enum": [ - "json_object", - "json_schema" - ] - }, - "json_schema": {} - } - }, - "raw": { - "type": "boolean", - "default": false, - "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." - }, - "stream": { - "type": "boolean", - "default": false, - "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." - }, - "max_tokens": { - "type": "integer", - "default": 256, - "description": "The maximum number of tokens to generate in the response." - }, - "temperature": { - "type": "number", - "default": 0.6, - "minimum": 0, - "maximum": 5, - "description": "Controls the randomness of the output; higher values produce more random results." - }, - "top_p": { - "type": "number", - "minimum": 0.001, - "maximum": 1, - "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." - }, - "top_k": { - "type": "integer", - "minimum": 1, - "maximum": 50, - "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." - }, - "seed": { - "type": "integer", - "minimum": 1, - "maximum": 9999999999, - "description": "Random seed for reproducibility of the generation." - }, - "repetition_penalty": { - "type": "number", - "minimum": 0, - "maximum": 2, - "description": "Penalty for repeated tokens; higher values discourage repetition." - }, - "frequency_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Decreases the likelihood of the model repeating the same lines verbatim." - }, - "presence_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Increases the likelihood of the model introducing new topics." - } - }, - "required": [ - "messages" - ] - } - ] - }, - "output": { - "oneOf": [ - { - "type": "object", - "properties": { - "response": { - "type": "string", - "description": "The generated text response from the model" - }, - "usage": { - "type": "object", - "description": "Usage statistics for the inference request", - "properties": { - "prompt_tokens": { - "type": "number", - "description": "Total number of tokens in input", - "default": 0 - }, - "completion_tokens": { - "type": "number", - "description": "Total number of tokens in output", - "default": 0 - }, - "total_tokens": { - "type": "number", - "description": "Total number of input and output tokens", - "default": 0 - } - } - }, - "tool_calls": { - "type": "array", - "description": "An array of tool calls requests made during the response generation", - "items": { - "type": "object", - "properties": { - "arguments": { - "type": "object", - "description": "The arguments passed to be passed to the tool call request" - }, - "name": { - "type": "string", - "description": "The name of the tool to be called" - } - } - } - } - }, - "required": [ - "response" - ] - }, - { - "type": "string", - "format": "binary" - } - ] - } - } -} \ No newline at end of file diff --git a/src/content/workers-ai-models/deepseek-math-7b-instruct.json b/src/content/workers-ai-models/deepseek-math-7b-instruct.json deleted file mode 100644 index a157b824a6933d9..000000000000000 --- a/src/content/workers-ai-models/deepseek-math-7b-instruct.json +++ /dev/null @@ -1,470 +0,0 @@ -{ - "id": "4c3a544e-da47-4336-9cea-c7cbfab33f16", - "source": 1, - "name": "@cf/deepseek-ai/deepseek-math-7b-instruct", - "description": "DeepSeekMath-Instruct 7B is a mathematically instructed tuning model derived from DeepSeekMath-Base 7B. DeepSeekMath is initialized with DeepSeek-Coder-v1.5 7B and continues pre-training on math-related tokens sourced from Common Crawl, together with natural language and code data for 500B tokens.", - "task": { - "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", - "name": "Text Generation", - "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." - }, - "created_at": "2024-02-27 17:54:17.459", - "tags": [], - "properties": [ - { - "property_id": "beta", - "value": "true" - }, - { - "property_id": "context_window", - "value": "4096" - }, - { - "property_id": "info", - "value": "https://huggingface.co/deepseek-ai/deepseek-math-7b-instruct" - }, - { - "property_id": "planned_deprecation_date", - "value": "2025-10-01" - }, - { - "property_id": "terms", - "value": "https://github.com/deepseek-ai/DeepSeek-Math/blob/main/LICENSE-MODEL" - } - ], - "schema": { - "input": { - "type": "object", - "oneOf": [ - { - "title": "Prompt", - "properties": { - "prompt": { - "type": "string", - "minLength": 1, - "description": "The input text prompt for the model to generate a response." - }, - "lora": { - "type": "string", - "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." - }, - "response_format": { - "title": "JSON Mode", - "type": "object", - "properties": { - "type": { - "type": "string", - "enum": [ - "json_object", - "json_schema" - ] - }, - "json_schema": {} - } - }, - "raw": { - "type": "boolean", - "default": false, - "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." - }, - "stream": { - "type": "boolean", - "default": false, - "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." - }, - "max_tokens": { - "type": "integer", - "default": 256, - "description": "The maximum number of tokens to generate in the response." - }, - "temperature": { - "type": "number", - "default": 0.6, - "minimum": 0, - "maximum": 5, - "description": "Controls the randomness of the output; higher values produce more random results." - }, - "top_p": { - "type": "number", - "minimum": 0.001, - "maximum": 1, - "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." - }, - "top_k": { - "type": "integer", - "minimum": 1, - "maximum": 50, - "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." - }, - "seed": { - "type": "integer", - "minimum": 1, - "maximum": 9999999999, - "description": "Random seed for reproducibility of the generation." - }, - "repetition_penalty": { - "type": "number", - "minimum": 0, - "maximum": 2, - "description": "Penalty for repeated tokens; higher values discourage repetition." - }, - "frequency_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Decreases the likelihood of the model repeating the same lines verbatim." - }, - "presence_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Increases the likelihood of the model introducing new topics." - } - }, - "required": [ - "prompt" - ] - }, - { - "title": "Messages", - "properties": { - "messages": { - "type": "array", - "description": "An array of message objects representing the conversation history.", - "items": { - "type": "object", - "properties": { - "role": { - "type": "string", - "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." - }, - "content": { - "oneOf": [ - { - "type": "string", - "description": "The content of the message as a string." - }, - { - "type": "array", - "description": "Array of text content parts.", - "items": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "Type of the content (text)" - }, - "text": { - "type": "string", - "description": "Text content" - } - } - } - } - ] - } - }, - "required": [ - "role", - "content" - ] - } - }, - "functions": { - "type": "array", - "items": { - "type": "object", - "properties": { - "name": { - "type": "string" - }, - "code": { - "type": "string" - } - }, - "required": [ - "name", - "code" - ] - } - }, - "tools": { - "type": "array", - "description": "A list of tools available for the assistant to use.", - "items": { - "type": "object", - "oneOf": [ - { - "properties": { - "name": { - "type": "string", - "description": "The name of the tool. More descriptive the better." - }, - "description": { - "type": "string", - "description": "A brief description of what the tool does." - }, - "parameters": { - "type": "object", - "description": "Schema defining the parameters accepted by the tool.", - "properties": { - "type": { - "type": "string", - "description": "The type of the parameters object (usually 'object')." - }, - "required": { - "type": "array", - "description": "List of required parameter names.", - "items": { - "type": "string" - } - }, - "properties": { - "type": "object", - "description": "Definitions of each parameter.", - "additionalProperties": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "The data type of the parameter." - }, - "description": { - "type": "string", - "description": "A description of the expected parameter." - } - }, - "required": [ - "type", - "description" - ] - } - } - }, - "required": [ - "type", - "properties" - ] - } - }, - "required": [ - "name", - "description", - "parameters" - ] - }, - { - "properties": { - "type": { - "type": "string", - "description": "Specifies the type of tool (e.g., 'function')." - }, - "function": { - "type": "object", - "description": "Details of the function tool.", - "properties": { - "name": { - "type": "string", - "description": "The name of the function." - }, - "description": { - "type": "string", - "description": "A brief description of what the function does." - }, - "parameters": { - "type": "object", - "description": "Schema defining the parameters accepted by the function.", - "properties": { - "type": { - "type": "string", - "description": "The type of the parameters object (usually 'object')." - }, - "required": { - "type": "array", - "description": "List of required parameter names.", - "items": { - "type": "string" - } - }, - "properties": { - "type": "object", - "description": "Definitions of each parameter.", - "additionalProperties": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "The data type of the parameter." - }, - "description": { - "type": "string", - "description": "A description of the expected parameter." - } - }, - "required": [ - "type", - "description" - ] - } - } - }, - "required": [ - "type", - "properties" - ] - } - }, - "required": [ - "name", - "description", - "parameters" - ] - } - }, - "required": [ - "type", - "function" - ] - } - ] - } - }, - "response_format": { - "title": "JSON Mode", - "type": "object", - "properties": { - "type": { - "type": "string", - "enum": [ - "json_object", - "json_schema" - ] - }, - "json_schema": {} - } - }, - "raw": { - "type": "boolean", - "default": false, - "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." - }, - "stream": { - "type": "boolean", - "default": false, - "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." - }, - "max_tokens": { - "type": "integer", - "default": 256, - "description": "The maximum number of tokens to generate in the response." - }, - "temperature": { - "type": "number", - "default": 0.6, - "minimum": 0, - "maximum": 5, - "description": "Controls the randomness of the output; higher values produce more random results." - }, - "top_p": { - "type": "number", - "minimum": 0.001, - "maximum": 1, - "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." - }, - "top_k": { - "type": "integer", - "minimum": 1, - "maximum": 50, - "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." - }, - "seed": { - "type": "integer", - "minimum": 1, - "maximum": 9999999999, - "description": "Random seed for reproducibility of the generation." - }, - "repetition_penalty": { - "type": "number", - "minimum": 0, - "maximum": 2, - "description": "Penalty for repeated tokens; higher values discourage repetition." - }, - "frequency_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Decreases the likelihood of the model repeating the same lines verbatim." - }, - "presence_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Increases the likelihood of the model introducing new topics." - } - }, - "required": [ - "messages" - ] - } - ] - }, - "output": { - "oneOf": [ - { - "type": "object", - "properties": { - "response": { - "type": "string", - "description": "The generated text response from the model" - }, - "usage": { - "type": "object", - "description": "Usage statistics for the inference request", - "properties": { - "prompt_tokens": { - "type": "number", - "description": "Total number of tokens in input", - "default": 0 - }, - "completion_tokens": { - "type": "number", - "description": "Total number of tokens in output", - "default": 0 - }, - "total_tokens": { - "type": "number", - "description": "Total number of input and output tokens", - "default": 0 - } - } - }, - "tool_calls": { - "type": "array", - "description": "An array of tool calls requests made during the response generation", - "items": { - "type": "object", - "properties": { - "arguments": { - "type": "object", - "description": "The arguments passed to be passed to the tool call request" - }, - "name": { - "type": "string", - "description": "The name of the tool to be called" - } - } - } - } - }, - "required": [ - "response" - ] - }, - { - "type": "string", - "format": "binary" - } - ] - } - } -} \ No newline at end of file diff --git a/src/content/workers-ai-models/discolm-german-7b-v1-awq.json b/src/content/workers-ai-models/discolm-german-7b-v1-awq.json deleted file mode 100644 index f3dccd2f1a14d0d..000000000000000 --- a/src/content/workers-ai-models/discolm-german-7b-v1-awq.json +++ /dev/null @@ -1,466 +0,0 @@ -{ - "id": "9d2ab560-065e-4d0d-a789-d4bc7468d33e", - "source": 1, - "name": "@cf/thebloke/discolm-german-7b-v1-awq", - "description": "DiscoLM German 7b is a Mistral-based large language model with a focus on German-language applications. AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization.", - "task": { - "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", - "name": "Text Generation", - "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." - }, - "created_at": "2024-02-27 18:23:05.178", - "tags": [], - "properties": [ - { - "property_id": "beta", - "value": "true" - }, - { - "property_id": "context_window", - "value": "4096" - }, - { - "property_id": "info", - "value": "https://huggingface.co/TheBloke/DiscoLM_German_7b_v1-AWQ" - }, - { - "property_id": "planned_deprecation_date", - "value": "2025-10-01" - } - ], - "schema": { - "input": { - "type": "object", - "oneOf": [ - { - "title": "Prompt", - "properties": { - "prompt": { - "type": "string", - "minLength": 1, - "description": "The input text prompt for the model to generate a response." - }, - "lora": { - "type": "string", - "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." - }, - "response_format": { - "title": "JSON Mode", - "type": "object", - "properties": { - "type": { - "type": "string", - "enum": [ - "json_object", - "json_schema" - ] - }, - "json_schema": {} - } - }, - "raw": { - "type": "boolean", - "default": false, - "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." - }, - "stream": { - "type": "boolean", - "default": false, - "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." - }, - "max_tokens": { - "type": "integer", - "default": 256, - "description": "The maximum number of tokens to generate in the response." - }, - "temperature": { - "type": "number", - "default": 0.6, - "minimum": 0, - "maximum": 5, - "description": "Controls the randomness of the output; higher values produce more random results." - }, - "top_p": { - "type": "number", - "minimum": 0.001, - "maximum": 1, - "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." - }, - "top_k": { - "type": "integer", - "minimum": 1, - "maximum": 50, - "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." - }, - "seed": { - "type": "integer", - "minimum": 1, - "maximum": 9999999999, - "description": "Random seed for reproducibility of the generation." - }, - "repetition_penalty": { - "type": "number", - "minimum": 0, - "maximum": 2, - "description": "Penalty for repeated tokens; higher values discourage repetition." - }, - "frequency_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Decreases the likelihood of the model repeating the same lines verbatim." - }, - "presence_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Increases the likelihood of the model introducing new topics." - } - }, - "required": [ - "prompt" - ] - }, - { - "title": "Messages", - "properties": { - "messages": { - "type": "array", - "description": "An array of message objects representing the conversation history.", - "items": { - "type": "object", - "properties": { - "role": { - "type": "string", - "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." - }, - "content": { - "oneOf": [ - { - "type": "string", - "description": "The content of the message as a string." - }, - { - "type": "array", - "description": "Array of text content parts.", - "items": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "Type of the content (text)" - }, - "text": { - "type": "string", - "description": "Text content" - } - } - } - } - ] - } - }, - "required": [ - "role", - "content" - ] - } - }, - "functions": { - "type": "array", - "items": { - "type": "object", - "properties": { - "name": { - "type": "string" - }, - "code": { - "type": "string" - } - }, - "required": [ - "name", - "code" - ] - } - }, - "tools": { - "type": "array", - "description": "A list of tools available for the assistant to use.", - "items": { - "type": "object", - "oneOf": [ - { - "properties": { - "name": { - "type": "string", - "description": "The name of the tool. More descriptive the better." - }, - "description": { - "type": "string", - "description": "A brief description of what the tool does." - }, - "parameters": { - "type": "object", - "description": "Schema defining the parameters accepted by the tool.", - "properties": { - "type": { - "type": "string", - "description": "The type of the parameters object (usually 'object')." - }, - "required": { - "type": "array", - "description": "List of required parameter names.", - "items": { - "type": "string" - } - }, - "properties": { - "type": "object", - "description": "Definitions of each parameter.", - "additionalProperties": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "The data type of the parameter." - }, - "description": { - "type": "string", - "description": "A description of the expected parameter." - } - }, - "required": [ - "type", - "description" - ] - } - } - }, - "required": [ - "type", - "properties" - ] - } - }, - "required": [ - "name", - "description", - "parameters" - ] - }, - { - "properties": { - "type": { - "type": "string", - "description": "Specifies the type of tool (e.g., 'function')." - }, - "function": { - "type": "object", - "description": "Details of the function tool.", - "properties": { - "name": { - "type": "string", - "description": "The name of the function." - }, - "description": { - "type": "string", - "description": "A brief description of what the function does." - }, - "parameters": { - "type": "object", - "description": "Schema defining the parameters accepted by the function.", - "properties": { - "type": { - "type": "string", - "description": "The type of the parameters object (usually 'object')." - }, - "required": { - "type": "array", - "description": "List of required parameter names.", - "items": { - "type": "string" - } - }, - "properties": { - "type": "object", - "description": "Definitions of each parameter.", - "additionalProperties": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "The data type of the parameter." - }, - "description": { - "type": "string", - "description": "A description of the expected parameter." - } - }, - "required": [ - "type", - "description" - ] - } - } - }, - "required": [ - "type", - "properties" - ] - } - }, - "required": [ - "name", - "description", - "parameters" - ] - } - }, - "required": [ - "type", - "function" - ] - } - ] - } - }, - "response_format": { - "title": "JSON Mode", - "type": "object", - "properties": { - "type": { - "type": "string", - "enum": [ - "json_object", - "json_schema" - ] - }, - "json_schema": {} - } - }, - "raw": { - "type": "boolean", - "default": false, - "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." - }, - "stream": { - "type": "boolean", - "default": false, - "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." - }, - "max_tokens": { - "type": "integer", - "default": 256, - "description": "The maximum number of tokens to generate in the response." - }, - "temperature": { - "type": "number", - "default": 0.6, - "minimum": 0, - "maximum": 5, - "description": "Controls the randomness of the output; higher values produce more random results." - }, - "top_p": { - "type": "number", - "minimum": 0.001, - "maximum": 1, - "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." - }, - "top_k": { - "type": "integer", - "minimum": 1, - "maximum": 50, - "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." - }, - "seed": { - "type": "integer", - "minimum": 1, - "maximum": 9999999999, - "description": "Random seed for reproducibility of the generation." - }, - "repetition_penalty": { - "type": "number", - "minimum": 0, - "maximum": 2, - "description": "Penalty for repeated tokens; higher values discourage repetition." - }, - "frequency_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Decreases the likelihood of the model repeating the same lines verbatim." - }, - "presence_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Increases the likelihood of the model introducing new topics." - } - }, - "required": [ - "messages" - ] - } - ] - }, - "output": { - "oneOf": [ - { - "type": "object", - "properties": { - "response": { - "type": "string", - "description": "The generated text response from the model" - }, - "usage": { - "type": "object", - "description": "Usage statistics for the inference request", - "properties": { - "prompt_tokens": { - "type": "number", - "description": "Total number of tokens in input", - "default": 0 - }, - "completion_tokens": { - "type": "number", - "description": "Total number of tokens in output", - "default": 0 - }, - "total_tokens": { - "type": "number", - "description": "Total number of input and output tokens", - "default": 0 - } - } - }, - "tool_calls": { - "type": "array", - "description": "An array of tool calls requests made during the response generation", - "items": { - "type": "object", - "properties": { - "arguments": { - "type": "object", - "description": "The arguments passed to be passed to the tool call request" - }, - "name": { - "type": "string", - "description": "The name of the tool to be called" - } - } - } - } - }, - "required": [ - "response" - ] - }, - { - "type": "string", - "format": "binary" - } - ] - } - } -} \ No newline at end of file diff --git a/src/content/workers-ai-models/falcon-7b-instruct.json b/src/content/workers-ai-models/falcon-7b-instruct.json deleted file mode 100644 index d8f8f7b73c9f43e..000000000000000 --- a/src/content/workers-ai-models/falcon-7b-instruct.json +++ /dev/null @@ -1,466 +0,0 @@ -{ - "id": "48dd2443-0c61-43b2-8894-22abddf1b081", - "source": 1, - "name": "@cf/tiiuae/falcon-7b-instruct", - "description": "Falcon-7B-Instruct is a 7B parameters causal decoder-only model built by TII based on Falcon-7B and finetuned on a mixture of chat/instruct datasets.", - "task": { - "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", - "name": "Text Generation", - "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." - }, - "created_at": "2024-02-27 18:21:15.796", - "tags": [], - "properties": [ - { - "property_id": "beta", - "value": "true" - }, - { - "property_id": "context_window", - "value": "4096" - }, - { - "property_id": "info", - "value": "https://huggingface.co/tiiuae/falcon-7b-instruct" - }, - { - "property_id": "planned_deprecation_date", - "value": "2025-10-01" - } - ], - "schema": { - "input": { - "type": "object", - "oneOf": [ - { - "title": "Prompt", - "properties": { - "prompt": { - "type": "string", - "minLength": 1, - "description": "The input text prompt for the model to generate a response." - }, - "lora": { - "type": "string", - "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." - }, - "response_format": { - "title": "JSON Mode", - "type": "object", - "properties": { - "type": { - "type": "string", - "enum": [ - "json_object", - "json_schema" - ] - }, - "json_schema": {} - } - }, - "raw": { - "type": "boolean", - "default": false, - "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." - }, - "stream": { - "type": "boolean", - "default": false, - "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." - }, - "max_tokens": { - "type": "integer", - "default": 256, - "description": "The maximum number of tokens to generate in the response." - }, - "temperature": { - "type": "number", - "default": 0.6, - "minimum": 0, - "maximum": 5, - "description": "Controls the randomness of the output; higher values produce more random results." - }, - "top_p": { - "type": "number", - "minimum": 0.001, - "maximum": 1, - "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." - }, - "top_k": { - "type": "integer", - "minimum": 1, - "maximum": 50, - "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." - }, - "seed": { - "type": "integer", - "minimum": 1, - "maximum": 9999999999, - "description": "Random seed for reproducibility of the generation." - }, - "repetition_penalty": { - "type": "number", - "minimum": 0, - "maximum": 2, - "description": "Penalty for repeated tokens; higher values discourage repetition." - }, - "frequency_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Decreases the likelihood of the model repeating the same lines verbatim." - }, - "presence_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Increases the likelihood of the model introducing new topics." - } - }, - "required": [ - "prompt" - ] - }, - { - "title": "Messages", - "properties": { - "messages": { - "type": "array", - "description": "An array of message objects representing the conversation history.", - "items": { - "type": "object", - "properties": { - "role": { - "type": "string", - "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." - }, - "content": { - "oneOf": [ - { - "type": "string", - "description": "The content of the message as a string." - }, - { - "type": "array", - "description": "Array of text content parts.", - "items": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "Type of the content (text)" - }, - "text": { - "type": "string", - "description": "Text content" - } - } - } - } - ] - } - }, - "required": [ - "role", - "content" - ] - } - }, - "functions": { - "type": "array", - "items": { - "type": "object", - "properties": { - "name": { - "type": "string" - }, - "code": { - "type": "string" - } - }, - "required": [ - "name", - "code" - ] - } - }, - "tools": { - "type": "array", - "description": "A list of tools available for the assistant to use.", - "items": { - "type": "object", - "oneOf": [ - { - "properties": { - "name": { - "type": "string", - "description": "The name of the tool. More descriptive the better." - }, - "description": { - "type": "string", - "description": "A brief description of what the tool does." - }, - "parameters": { - "type": "object", - "description": "Schema defining the parameters accepted by the tool.", - "properties": { - "type": { - "type": "string", - "description": "The type of the parameters object (usually 'object')." - }, - "required": { - "type": "array", - "description": "List of required parameter names.", - "items": { - "type": "string" - } - }, - "properties": { - "type": "object", - "description": "Definitions of each parameter.", - "additionalProperties": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "The data type of the parameter." - }, - "description": { - "type": "string", - "description": "A description of the expected parameter." - } - }, - "required": [ - "type", - "description" - ] - } - } - }, - "required": [ - "type", - "properties" - ] - } - }, - "required": [ - "name", - "description", - "parameters" - ] - }, - { - "properties": { - "type": { - "type": "string", - "description": "Specifies the type of tool (e.g., 'function')." - }, - "function": { - "type": "object", - "description": "Details of the function tool.", - "properties": { - "name": { - "type": "string", - "description": "The name of the function." - }, - "description": { - "type": "string", - "description": "A brief description of what the function does." - }, - "parameters": { - "type": "object", - "description": "Schema defining the parameters accepted by the function.", - "properties": { - "type": { - "type": "string", - "description": "The type of the parameters object (usually 'object')." - }, - "required": { - "type": "array", - "description": "List of required parameter names.", - "items": { - "type": "string" - } - }, - "properties": { - "type": "object", - "description": "Definitions of each parameter.", - "additionalProperties": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "The data type of the parameter." - }, - "description": { - "type": "string", - "description": "A description of the expected parameter." - } - }, - "required": [ - "type", - "description" - ] - } - } - }, - "required": [ - "type", - "properties" - ] - } - }, - "required": [ - "name", - "description", - "parameters" - ] - } - }, - "required": [ - "type", - "function" - ] - } - ] - } - }, - "response_format": { - "title": "JSON Mode", - "type": "object", - "properties": { - "type": { - "type": "string", - "enum": [ - "json_object", - "json_schema" - ] - }, - "json_schema": {} - } - }, - "raw": { - "type": "boolean", - "default": false, - "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." - }, - "stream": { - "type": "boolean", - "default": false, - "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." - }, - "max_tokens": { - "type": "integer", - "default": 256, - "description": "The maximum number of tokens to generate in the response." - }, - "temperature": { - "type": "number", - "default": 0.6, - "minimum": 0, - "maximum": 5, - "description": "Controls the randomness of the output; higher values produce more random results." - }, - "top_p": { - "type": "number", - "minimum": 0.001, - "maximum": 1, - "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." - }, - "top_k": { - "type": "integer", - "minimum": 1, - "maximum": 50, - "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." - }, - "seed": { - "type": "integer", - "minimum": 1, - "maximum": 9999999999, - "description": "Random seed for reproducibility of the generation." - }, - "repetition_penalty": { - "type": "number", - "minimum": 0, - "maximum": 2, - "description": "Penalty for repeated tokens; higher values discourage repetition." - }, - "frequency_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Decreases the likelihood of the model repeating the same lines verbatim." - }, - "presence_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Increases the likelihood of the model introducing new topics." - } - }, - "required": [ - "messages" - ] - } - ] - }, - "output": { - "oneOf": [ - { - "type": "object", - "properties": { - "response": { - "type": "string", - "description": "The generated text response from the model" - }, - "usage": { - "type": "object", - "description": "Usage statistics for the inference request", - "properties": { - "prompt_tokens": { - "type": "number", - "description": "Total number of tokens in input", - "default": 0 - }, - "completion_tokens": { - "type": "number", - "description": "Total number of tokens in output", - "default": 0 - }, - "total_tokens": { - "type": "number", - "description": "Total number of input and output tokens", - "default": 0 - } - } - }, - "tool_calls": { - "type": "array", - "description": "An array of tool calls requests made during the response generation", - "items": { - "type": "object", - "properties": { - "arguments": { - "type": "object", - "description": "The arguments passed to be passed to the tool call request" - }, - "name": { - "type": "string", - "description": "The name of the tool to be called" - } - } - } - } - }, - "required": [ - "response" - ] - }, - { - "type": "string", - "format": "binary" - } - ] - } - } -} \ No newline at end of file diff --git a/src/content/workers-ai-models/llama-2-13b-chat-awq.json b/src/content/workers-ai-models/llama-2-13b-chat-awq.json deleted file mode 100644 index 231fa04b905c684..000000000000000 --- a/src/content/workers-ai-models/llama-2-13b-chat-awq.json +++ /dev/null @@ -1,466 +0,0 @@ -{ - "id": "85c5a3c6-24b0-45e7-b23a-023182578822", - "source": 2, - "name": "@hf/thebloke/llama-2-13b-chat-awq", - "description": "Llama 2 13B Chat AWQ is an efficient, accurate and blazing-fast low-bit weight quantized Llama 2 variant.", - "task": { - "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", - "name": "Text Generation", - "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." - }, - "created_at": "2023-11-24 00:27:15.869", - "tags": [], - "properties": [ - { - "property_id": "beta", - "value": "true" - }, - { - "property_id": "context_window", - "value": "4096" - }, - { - "property_id": "info", - "value": "https://huggingface.co/TheBloke/Llama-2-13B-chat-AWQ" - }, - { - "property_id": "planned_deprecation_date", - "value": "2025-10-01" - } - ], - "schema": { - "input": { - "type": "object", - "oneOf": [ - { - "title": "Prompt", - "properties": { - "prompt": { - "type": "string", - "minLength": 1, - "description": "The input text prompt for the model to generate a response." - }, - "lora": { - "type": "string", - "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." - }, - "response_format": { - "title": "JSON Mode", - "type": "object", - "properties": { - "type": { - "type": "string", - "enum": [ - "json_object", - "json_schema" - ] - }, - "json_schema": {} - } - }, - "raw": { - "type": "boolean", - "default": false, - "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." - }, - "stream": { - "type": "boolean", - "default": false, - "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." - }, - "max_tokens": { - "type": "integer", - "default": 256, - "description": "The maximum number of tokens to generate in the response." - }, - "temperature": { - "type": "number", - "default": 0.6, - "minimum": 0, - "maximum": 5, - "description": "Controls the randomness of the output; higher values produce more random results." - }, - "top_p": { - "type": "number", - "minimum": 0.001, - "maximum": 1, - "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." - }, - "top_k": { - "type": "integer", - "minimum": 1, - "maximum": 50, - "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." - }, - "seed": { - "type": "integer", - "minimum": 1, - "maximum": 9999999999, - "description": "Random seed for reproducibility of the generation." - }, - "repetition_penalty": { - "type": "number", - "minimum": 0, - "maximum": 2, - "description": "Penalty for repeated tokens; higher values discourage repetition." - }, - "frequency_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Decreases the likelihood of the model repeating the same lines verbatim." - }, - "presence_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Increases the likelihood of the model introducing new topics." - } - }, - "required": [ - "prompt" - ] - }, - { - "title": "Messages", - "properties": { - "messages": { - "type": "array", - "description": "An array of message objects representing the conversation history.", - "items": { - "type": "object", - "properties": { - "role": { - "type": "string", - "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." - }, - "content": { - "oneOf": [ - { - "type": "string", - "description": "The content of the message as a string." - }, - { - "type": "array", - "description": "Array of text content parts.", - "items": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "Type of the content (text)" - }, - "text": { - "type": "string", - "description": "Text content" - } - } - } - } - ] - } - }, - "required": [ - "role", - "content" - ] - } - }, - "functions": { - "type": "array", - "items": { - "type": "object", - "properties": { - "name": { - "type": "string" - }, - "code": { - "type": "string" - } - }, - "required": [ - "name", - "code" - ] - } - }, - "tools": { - "type": "array", - "description": "A list of tools available for the assistant to use.", - "items": { - "type": "object", - "oneOf": [ - { - "properties": { - "name": { - "type": "string", - "description": "The name of the tool. More descriptive the better." - }, - "description": { - "type": "string", - "description": "A brief description of what the tool does." - }, - "parameters": { - "type": "object", - "description": "Schema defining the parameters accepted by the tool.", - "properties": { - "type": { - "type": "string", - "description": "The type of the parameters object (usually 'object')." - }, - "required": { - "type": "array", - "description": "List of required parameter names.", - "items": { - "type": "string" - } - }, - "properties": { - "type": "object", - "description": "Definitions of each parameter.", - "additionalProperties": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "The data type of the parameter." - }, - "description": { - "type": "string", - "description": "A description of the expected parameter." - } - }, - "required": [ - "type", - "description" - ] - } - } - }, - "required": [ - "type", - "properties" - ] - } - }, - "required": [ - "name", - "description", - "parameters" - ] - }, - { - "properties": { - "type": { - "type": "string", - "description": "Specifies the type of tool (e.g., 'function')." - }, - "function": { - "type": "object", - "description": "Details of the function tool.", - "properties": { - "name": { - "type": "string", - "description": "The name of the function." - }, - "description": { - "type": "string", - "description": "A brief description of what the function does." - }, - "parameters": { - "type": "object", - "description": "Schema defining the parameters accepted by the function.", - "properties": { - "type": { - "type": "string", - "description": "The type of the parameters object (usually 'object')." - }, - "required": { - "type": "array", - "description": "List of required parameter names.", - "items": { - "type": "string" - } - }, - "properties": { - "type": "object", - "description": "Definitions of each parameter.", - "additionalProperties": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "The data type of the parameter." - }, - "description": { - "type": "string", - "description": "A description of the expected parameter." - } - }, - "required": [ - "type", - "description" - ] - } - } - }, - "required": [ - "type", - "properties" - ] - } - }, - "required": [ - "name", - "description", - "parameters" - ] - } - }, - "required": [ - "type", - "function" - ] - } - ] - } - }, - "response_format": { - "title": "JSON Mode", - "type": "object", - "properties": { - "type": { - "type": "string", - "enum": [ - "json_object", - "json_schema" - ] - }, - "json_schema": {} - } - }, - "raw": { - "type": "boolean", - "default": false, - "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." - }, - "stream": { - "type": "boolean", - "default": false, - "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." - }, - "max_tokens": { - "type": "integer", - "default": 256, - "description": "The maximum number of tokens to generate in the response." - }, - "temperature": { - "type": "number", - "default": 0.6, - "minimum": 0, - "maximum": 5, - "description": "Controls the randomness of the output; higher values produce more random results." - }, - "top_p": { - "type": "number", - "minimum": 0.001, - "maximum": 1, - "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." - }, - "top_k": { - "type": "integer", - "minimum": 1, - "maximum": 50, - "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." - }, - "seed": { - "type": "integer", - "minimum": 1, - "maximum": 9999999999, - "description": "Random seed for reproducibility of the generation." - }, - "repetition_penalty": { - "type": "number", - "minimum": 0, - "maximum": 2, - "description": "Penalty for repeated tokens; higher values discourage repetition." - }, - "frequency_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Decreases the likelihood of the model repeating the same lines verbatim." - }, - "presence_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Increases the likelihood of the model introducing new topics." - } - }, - "required": [ - "messages" - ] - } - ] - }, - "output": { - "oneOf": [ - { - "type": "object", - "properties": { - "response": { - "type": "string", - "description": "The generated text response from the model" - }, - "usage": { - "type": "object", - "description": "Usage statistics for the inference request", - "properties": { - "prompt_tokens": { - "type": "number", - "description": "Total number of tokens in input", - "default": 0 - }, - "completion_tokens": { - "type": "number", - "description": "Total number of tokens in output", - "default": 0 - }, - "total_tokens": { - "type": "number", - "description": "Total number of input and output tokens", - "default": 0 - } - } - }, - "tool_calls": { - "type": "array", - "description": "An array of tool calls requests made during the response generation", - "items": { - "type": "object", - "properties": { - "arguments": { - "type": "object", - "description": "The arguments passed to be passed to the tool call request" - }, - "name": { - "type": "string", - "description": "The name of the tool to be called" - } - } - } - } - }, - "required": [ - "response" - ] - }, - { - "type": "string", - "format": "binary" - } - ] - } - } -} \ No newline at end of file diff --git a/src/content/workers-ai-models/llamaguard-7b-awq.json b/src/content/workers-ai-models/llamaguard-7b-awq.json deleted file mode 100644 index ab959c81d129317..000000000000000 --- a/src/content/workers-ai-models/llamaguard-7b-awq.json +++ /dev/null @@ -1,446 +0,0 @@ -{ - "id": "d9b7a55c-cefa-4208-8ab3-11497a2b046c", - "source": 2, - "name": "@hf/thebloke/llamaguard-7b-awq", - "description": "Llama Guard is a model for classifying the safety of LLM prompts and responses, using a taxonomy of safety risks.\n", - "task": { - "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", - "name": "Text Generation", - "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." - }, - "created_at": "2024-02-06 18:13:59.060", - "tags": [ - "moderation", - "safety", - "content-filtering", - "guardrails" - ], - "properties": [ - { - "property_id": "beta", - "value": "true" - }, - { - "property_id": "context_window", - "value": "4096" - }, - { - "property_id": "planned_deprecation_date", - "value": "2025-10-01" - } - ], - "schema": { - "input": { - "type": "object", - "oneOf": [ - { - "title": "Prompt", - "properties": { - "prompt": { - "type": "string", - "minLength": 1, - "description": "The input text prompt for the model to generate a response." - }, - "lora": { - "type": "string", - "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." - }, - "response_format": { - "title": "JSON Mode", - "type": "object", - "properties": { - "type": { - "type": "string", - "enum": [ - "json_object", - "json_schema" - ] - }, - "json_schema": {} - } - }, - "raw": { - "type": "boolean", - "default": false, - "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." - }, - "stream": { - "type": "boolean", - "default": false, - "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." - }, - "max_tokens": { - "type": "integer", - "default": 256, - "description": "The maximum number of tokens to generate in the response." - }, - "temperature": { - "type": "number", - "default": 0.6, - "minimum": 0, - "maximum": 5, - "description": "Controls the randomness of the output; higher values produce more random results." - }, - "top_p": { - "type": "number", - "minimum": 0.001, - "maximum": 1, - "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." - }, - "top_k": { - "type": "integer", - "minimum": 1, - "maximum": 50, - "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." - }, - "seed": { - "type": "integer", - "minimum": 1, - "maximum": 9999999999, - "description": "Random seed for reproducibility of the generation." - }, - "repetition_penalty": { - "type": "number", - "minimum": 0, - "maximum": 2, - "description": "Penalty for repeated tokens; higher values discourage repetition." - }, - "frequency_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Decreases the likelihood of the model repeating the same lines verbatim." - }, - "presence_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Increases the likelihood of the model introducing new topics." - } - }, - "required": [ - "prompt" - ] - }, - { - "title": "Messages", - "properties": { - "messages": { - "type": "array", - "description": "An array of message objects representing the conversation history.", - "items": { - "type": "object", - "properties": { - "role": { - "type": "string", - "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." - }, - "content": { - "type": "string", - "description": "The content of the message as a string." - } - }, - "required": [ - "role", - "content" - ] - } - }, - "functions": { - "type": "array", - "items": { - "type": "object", - "properties": { - "name": { - "type": "string" - }, - "code": { - "type": "string" - } - }, - "required": [ - "name", - "code" - ] - } - }, - "tools": { - "type": "array", - "description": "A list of tools available for the assistant to use.", - "items": { - "type": "object", - "oneOf": [ - { - "properties": { - "name": { - "type": "string", - "description": "The name of the tool. More descriptive the better." - }, - "description": { - "type": "string", - "description": "A brief description of what the tool does." - }, - "parameters": { - "type": "object", - "description": "Schema defining the parameters accepted by the tool.", - "properties": { - "type": { - "type": "string", - "description": "The type of the parameters object (usually 'object')." - }, - "required": { - "type": "array", - "description": "List of required parameter names.", - "items": { - "type": "string" - } - }, - "properties": { - "type": "object", - "description": "Definitions of each parameter.", - "additionalProperties": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "The data type of the parameter." - }, - "description": { - "type": "string", - "description": "A description of the expected parameter." - } - }, - "required": [ - "type", - "description" - ] - } - } - }, - "required": [ - "type", - "properties" - ] - } - }, - "required": [ - "name", - "description", - "parameters" - ] - }, - { - "properties": { - "type": { - "type": "string", - "description": "Specifies the type of tool (e.g., 'function')." - }, - "function": { - "type": "object", - "description": "Details of the function tool.", - "properties": { - "name": { - "type": "string", - "description": "The name of the function." - }, - "description": { - "type": "string", - "description": "A brief description of what the function does." - }, - "parameters": { - "type": "object", - "description": "Schema defining the parameters accepted by the function.", - "properties": { - "type": { - "type": "string", - "description": "The type of the parameters object (usually 'object')." - }, - "required": { - "type": "array", - "description": "List of required parameter names.", - "items": { - "type": "string" - } - }, - "properties": { - "type": "object", - "description": "Definitions of each parameter.", - "additionalProperties": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "The data type of the parameter." - }, - "description": { - "type": "string", - "description": "A description of the expected parameter." - } - }, - "required": [ - "type", - "description" - ] - } - } - }, - "required": [ - "type", - "properties" - ] - } - }, - "required": [ - "name", - "description", - "parameters" - ] - } - }, - "required": [ - "type", - "function" - ] - } - ] - } - }, - "response_format": { - "title": "JSON Mode", - "type": "object", - "properties": { - "type": { - "type": "string", - "enum": [ - "json_object", - "json_schema" - ] - }, - "json_schema": {} - } - }, - "raw": { - "type": "boolean", - "default": false, - "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." - }, - "stream": { - "type": "boolean", - "default": false, - "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." - }, - "max_tokens": { - "type": "integer", - "default": 256, - "description": "The maximum number of tokens to generate in the response." - }, - "temperature": { - "type": "number", - "default": 0.6, - "minimum": 0, - "maximum": 5, - "description": "Controls the randomness of the output; higher values produce more random results." - }, - "top_p": { - "type": "number", - "minimum": 0.001, - "maximum": 1, - "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." - }, - "top_k": { - "type": "integer", - "minimum": 1, - "maximum": 50, - "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." - }, - "seed": { - "type": "integer", - "minimum": 1, - "maximum": 9999999999, - "description": "Random seed for reproducibility of the generation." - }, - "repetition_penalty": { - "type": "number", - "minimum": 0, - "maximum": 2, - "description": "Penalty for repeated tokens; higher values discourage repetition." - }, - "frequency_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Decreases the likelihood of the model repeating the same lines verbatim." - }, - "presence_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Increases the likelihood of the model introducing new topics." - } - }, - "required": [ - "messages" - ] - } - ] - }, - "output": { - "oneOf": [ - { - "type": "object", - "properties": { - "response": { - "type": "string", - "description": "The generated text response from the model" - }, - "usage": { - "type": "object", - "description": "Usage statistics for the inference request", - "properties": { - "prompt_tokens": { - "type": "number", - "description": "Total number of tokens in input", - "default": 0 - }, - "completion_tokens": { - "type": "number", - "description": "Total number of tokens in output", - "default": 0 - }, - "total_tokens": { - "type": "number", - "description": "Total number of input and output tokens", - "default": 0 - } - } - }, - "tool_calls": { - "type": "array", - "description": "An array of tool calls requests made during the response generation", - "items": { - "type": "object", - "properties": { - "arguments": { - "type": "object", - "description": "The arguments passed to be passed to the tool call request" - }, - "name": { - "type": "string", - "description": "The name of the tool to be called" - } - } - } - } - }, - "required": [ - "response" - ] - }, - { - "type": "string", - "format": "binary" - } - ] - } - } -} \ No newline at end of file diff --git a/src/content/workers-ai-models/mistral-7b-instruct-v0.1-awq.json b/src/content/workers-ai-models/mistral-7b-instruct-v0.1-awq.json deleted file mode 100644 index 3f3212d05396292..000000000000000 --- a/src/content/workers-ai-models/mistral-7b-instruct-v0.1-awq.json +++ /dev/null @@ -1,466 +0,0 @@ -{ - "id": "980ec5e9-33c2-483a-a2d8-cd092fdf273f", - "source": 2, - "name": "@hf/thebloke/mistral-7b-instruct-v0.1-awq", - "description": "Mistral 7B Instruct v0.1 AWQ is an efficient, accurate and blazing-fast low-bit weight quantized Mistral variant.", - "task": { - "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", - "name": "Text Generation", - "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." - }, - "created_at": "2023-11-24 00:27:15.869", - "tags": [], - "properties": [ - { - "property_id": "beta", - "value": "true" - }, - { - "property_id": "context_window", - "value": "4096" - }, - { - "property_id": "info", - "value": "https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-AWQ" - }, - { - "property_id": "planned_deprecation_date", - "value": "2025-10-01" - } - ], - "schema": { - "input": { - "type": "object", - "oneOf": [ - { - "title": "Prompt", - "properties": { - "prompt": { - "type": "string", - "minLength": 1, - "description": "The input text prompt for the model to generate a response." - }, - "lora": { - "type": "string", - "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." - }, - "response_format": { - "title": "JSON Mode", - "type": "object", - "properties": { - "type": { - "type": "string", - "enum": [ - "json_object", - "json_schema" - ] - }, - "json_schema": {} - } - }, - "raw": { - "type": "boolean", - "default": false, - "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." - }, - "stream": { - "type": "boolean", - "default": false, - "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." - }, - "max_tokens": { - "type": "integer", - "default": 256, - "description": "The maximum number of tokens to generate in the response." - }, - "temperature": { - "type": "number", - "default": 0.6, - "minimum": 0, - "maximum": 5, - "description": "Controls the randomness of the output; higher values produce more random results." - }, - "top_p": { - "type": "number", - "minimum": 0.001, - "maximum": 1, - "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." - }, - "top_k": { - "type": "integer", - "minimum": 1, - "maximum": 50, - "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." - }, - "seed": { - "type": "integer", - "minimum": 1, - "maximum": 9999999999, - "description": "Random seed for reproducibility of the generation." - }, - "repetition_penalty": { - "type": "number", - "minimum": 0, - "maximum": 2, - "description": "Penalty for repeated tokens; higher values discourage repetition." - }, - "frequency_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Decreases the likelihood of the model repeating the same lines verbatim." - }, - "presence_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Increases the likelihood of the model introducing new topics." - } - }, - "required": [ - "prompt" - ] - }, - { - "title": "Messages", - "properties": { - "messages": { - "type": "array", - "description": "An array of message objects representing the conversation history.", - "items": { - "type": "object", - "properties": { - "role": { - "type": "string", - "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." - }, - "content": { - "oneOf": [ - { - "type": "string", - "description": "The content of the message as a string." - }, - { - "type": "array", - "description": "Array of text content parts.", - "items": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "Type of the content (text)" - }, - "text": { - "type": "string", - "description": "Text content" - } - } - } - } - ] - } - }, - "required": [ - "role", - "content" - ] - } - }, - "functions": { - "type": "array", - "items": { - "type": "object", - "properties": { - "name": { - "type": "string" - }, - "code": { - "type": "string" - } - }, - "required": [ - "name", - "code" - ] - } - }, - "tools": { - "type": "array", - "description": "A list of tools available for the assistant to use.", - "items": { - "type": "object", - "oneOf": [ - { - "properties": { - "name": { - "type": "string", - "description": "The name of the tool. More descriptive the better." - }, - "description": { - "type": "string", - "description": "A brief description of what the tool does." - }, - "parameters": { - "type": "object", - "description": "Schema defining the parameters accepted by the tool.", - "properties": { - "type": { - "type": "string", - "description": "The type of the parameters object (usually 'object')." - }, - "required": { - "type": "array", - "description": "List of required parameter names.", - "items": { - "type": "string" - } - }, - "properties": { - "type": "object", - "description": "Definitions of each parameter.", - "additionalProperties": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "The data type of the parameter." - }, - "description": { - "type": "string", - "description": "A description of the expected parameter." - } - }, - "required": [ - "type", - "description" - ] - } - } - }, - "required": [ - "type", - "properties" - ] - } - }, - "required": [ - "name", - "description", - "parameters" - ] - }, - { - "properties": { - "type": { - "type": "string", - "description": "Specifies the type of tool (e.g., 'function')." - }, - "function": { - "type": "object", - "description": "Details of the function tool.", - "properties": { - "name": { - "type": "string", - "description": "The name of the function." - }, - "description": { - "type": "string", - "description": "A brief description of what the function does." - }, - "parameters": { - "type": "object", - "description": "Schema defining the parameters accepted by the function.", - "properties": { - "type": { - "type": "string", - "description": "The type of the parameters object (usually 'object')." - }, - "required": { - "type": "array", - "description": "List of required parameter names.", - "items": { - "type": "string" - } - }, - "properties": { - "type": "object", - "description": "Definitions of each parameter.", - "additionalProperties": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "The data type of the parameter." - }, - "description": { - "type": "string", - "description": "A description of the expected parameter." - } - }, - "required": [ - "type", - "description" - ] - } - } - }, - "required": [ - "type", - "properties" - ] - } - }, - "required": [ - "name", - "description", - "parameters" - ] - } - }, - "required": [ - "type", - "function" - ] - } - ] - } - }, - "response_format": { - "title": "JSON Mode", - "type": "object", - "properties": { - "type": { - "type": "string", - "enum": [ - "json_object", - "json_schema" - ] - }, - "json_schema": {} - } - }, - "raw": { - "type": "boolean", - "default": false, - "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." - }, - "stream": { - "type": "boolean", - "default": false, - "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." - }, - "max_tokens": { - "type": "integer", - "default": 256, - "description": "The maximum number of tokens to generate in the response." - }, - "temperature": { - "type": "number", - "default": 0.6, - "minimum": 0, - "maximum": 5, - "description": "Controls the randomness of the output; higher values produce more random results." - }, - "top_p": { - "type": "number", - "minimum": 0.001, - "maximum": 1, - "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." - }, - "top_k": { - "type": "integer", - "minimum": 1, - "maximum": 50, - "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." - }, - "seed": { - "type": "integer", - "minimum": 1, - "maximum": 9999999999, - "description": "Random seed for reproducibility of the generation." - }, - "repetition_penalty": { - "type": "number", - "minimum": 0, - "maximum": 2, - "description": "Penalty for repeated tokens; higher values discourage repetition." - }, - "frequency_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Decreases the likelihood of the model repeating the same lines verbatim." - }, - "presence_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Increases the likelihood of the model introducing new topics." - } - }, - "required": [ - "messages" - ] - } - ] - }, - "output": { - "oneOf": [ - { - "type": "object", - "properties": { - "response": { - "type": "string", - "description": "The generated text response from the model" - }, - "usage": { - "type": "object", - "description": "Usage statistics for the inference request", - "properties": { - "prompt_tokens": { - "type": "number", - "description": "Total number of tokens in input", - "default": 0 - }, - "completion_tokens": { - "type": "number", - "description": "Total number of tokens in output", - "default": 0 - }, - "total_tokens": { - "type": "number", - "description": "Total number of input and output tokens", - "default": 0 - } - } - }, - "tool_calls": { - "type": "array", - "description": "An array of tool calls requests made during the response generation", - "items": { - "type": "object", - "properties": { - "arguments": { - "type": "object", - "description": "The arguments passed to be passed to the tool call request" - }, - "name": { - "type": "string", - "description": "The name of the tool to be called" - } - } - } - } - }, - "required": [ - "response" - ] - }, - { - "type": "string", - "format": "binary" - } - ] - } - } -} \ No newline at end of file diff --git a/src/content/workers-ai-models/neural-chat-7b-v3-1-awq.json b/src/content/workers-ai-models/neural-chat-7b-v3-1-awq.json deleted file mode 100644 index 1ca98b08aefca2b..000000000000000 --- a/src/content/workers-ai-models/neural-chat-7b-v3-1-awq.json +++ /dev/null @@ -1,462 +0,0 @@ -{ - "id": "d2ba5c6b-bbb7-49d6-b466-900654870cd6", - "source": 2, - "name": "@hf/thebloke/neural-chat-7b-v3-1-awq", - "description": "This model is a fine-tuned 7B parameter LLM on the Intel Gaudi 2 processor from the mistralai/Mistral-7B-v0.1 on the open source dataset Open-Orca/SlimOrca.", - "task": { - "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", - "name": "Text Generation", - "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." - }, - "created_at": "2024-02-06 18:12:30.722", - "tags": [], - "properties": [ - { - "property_id": "beta", - "value": "true" - }, - { - "property_id": "context_window", - "value": "4096" - }, - { - "property_id": "planned_deprecation_date", - "value": "2025-10-01" - } - ], - "schema": { - "input": { - "type": "object", - "oneOf": [ - { - "title": "Prompt", - "properties": { - "prompt": { - "type": "string", - "minLength": 1, - "description": "The input text prompt for the model to generate a response." - }, - "lora": { - "type": "string", - "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." - }, - "response_format": { - "title": "JSON Mode", - "type": "object", - "properties": { - "type": { - "type": "string", - "enum": [ - "json_object", - "json_schema" - ] - }, - "json_schema": {} - } - }, - "raw": { - "type": "boolean", - "default": false, - "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." - }, - "stream": { - "type": "boolean", - "default": false, - "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." - }, - "max_tokens": { - "type": "integer", - "default": 256, - "description": "The maximum number of tokens to generate in the response." - }, - "temperature": { - "type": "number", - "default": 0.6, - "minimum": 0, - "maximum": 5, - "description": "Controls the randomness of the output; higher values produce more random results." - }, - "top_p": { - "type": "number", - "minimum": 0.001, - "maximum": 1, - "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." - }, - "top_k": { - "type": "integer", - "minimum": 1, - "maximum": 50, - "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." - }, - "seed": { - "type": "integer", - "minimum": 1, - "maximum": 9999999999, - "description": "Random seed for reproducibility of the generation." - }, - "repetition_penalty": { - "type": "number", - "minimum": 0, - "maximum": 2, - "description": "Penalty for repeated tokens; higher values discourage repetition." - }, - "frequency_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Decreases the likelihood of the model repeating the same lines verbatim." - }, - "presence_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Increases the likelihood of the model introducing new topics." - } - }, - "required": [ - "prompt" - ] - }, - { - "title": "Messages", - "properties": { - "messages": { - "type": "array", - "description": "An array of message objects representing the conversation history.", - "items": { - "type": "object", - "properties": { - "role": { - "type": "string", - "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." - }, - "content": { - "oneOf": [ - { - "type": "string", - "description": "The content of the message as a string." - }, - { - "type": "array", - "description": "Array of text content parts.", - "items": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "Type of the content (text)" - }, - "text": { - "type": "string", - "description": "Text content" - } - } - } - } - ] - } - }, - "required": [ - "role", - "content" - ] - } - }, - "functions": { - "type": "array", - "items": { - "type": "object", - "properties": { - "name": { - "type": "string" - }, - "code": { - "type": "string" - } - }, - "required": [ - "name", - "code" - ] - } - }, - "tools": { - "type": "array", - "description": "A list of tools available for the assistant to use.", - "items": { - "type": "object", - "oneOf": [ - { - "properties": { - "name": { - "type": "string", - "description": "The name of the tool. More descriptive the better." - }, - "description": { - "type": "string", - "description": "A brief description of what the tool does." - }, - "parameters": { - "type": "object", - "description": "Schema defining the parameters accepted by the tool.", - "properties": { - "type": { - "type": "string", - "description": "The type of the parameters object (usually 'object')." - }, - "required": { - "type": "array", - "description": "List of required parameter names.", - "items": { - "type": "string" - } - }, - "properties": { - "type": "object", - "description": "Definitions of each parameter.", - "additionalProperties": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "The data type of the parameter." - }, - "description": { - "type": "string", - "description": "A description of the expected parameter." - } - }, - "required": [ - "type", - "description" - ] - } - } - }, - "required": [ - "type", - "properties" - ] - } - }, - "required": [ - "name", - "description", - "parameters" - ] - }, - { - "properties": { - "type": { - "type": "string", - "description": "Specifies the type of tool (e.g., 'function')." - }, - "function": { - "type": "object", - "description": "Details of the function tool.", - "properties": { - "name": { - "type": "string", - "description": "The name of the function." - }, - "description": { - "type": "string", - "description": "A brief description of what the function does." - }, - "parameters": { - "type": "object", - "description": "Schema defining the parameters accepted by the function.", - "properties": { - "type": { - "type": "string", - "description": "The type of the parameters object (usually 'object')." - }, - "required": { - "type": "array", - "description": "List of required parameter names.", - "items": { - "type": "string" - } - }, - "properties": { - "type": "object", - "description": "Definitions of each parameter.", - "additionalProperties": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "The data type of the parameter." - }, - "description": { - "type": "string", - "description": "A description of the expected parameter." - } - }, - "required": [ - "type", - "description" - ] - } - } - }, - "required": [ - "type", - "properties" - ] - } - }, - "required": [ - "name", - "description", - "parameters" - ] - } - }, - "required": [ - "type", - "function" - ] - } - ] - } - }, - "response_format": { - "title": "JSON Mode", - "type": "object", - "properties": { - "type": { - "type": "string", - "enum": [ - "json_object", - "json_schema" - ] - }, - "json_schema": {} - } - }, - "raw": { - "type": "boolean", - "default": false, - "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." - }, - "stream": { - "type": "boolean", - "default": false, - "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." - }, - "max_tokens": { - "type": "integer", - "default": 256, - "description": "The maximum number of tokens to generate in the response." - }, - "temperature": { - "type": "number", - "default": 0.6, - "minimum": 0, - "maximum": 5, - "description": "Controls the randomness of the output; higher values produce more random results." - }, - "top_p": { - "type": "number", - "minimum": 0.001, - "maximum": 1, - "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." - }, - "top_k": { - "type": "integer", - "minimum": 1, - "maximum": 50, - "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." - }, - "seed": { - "type": "integer", - "minimum": 1, - "maximum": 9999999999, - "description": "Random seed for reproducibility of the generation." - }, - "repetition_penalty": { - "type": "number", - "minimum": 0, - "maximum": 2, - "description": "Penalty for repeated tokens; higher values discourage repetition." - }, - "frequency_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Decreases the likelihood of the model repeating the same lines verbatim." - }, - "presence_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Increases the likelihood of the model introducing new topics." - } - }, - "required": [ - "messages" - ] - } - ] - }, - "output": { - "oneOf": [ - { - "type": "object", - "properties": { - "response": { - "type": "string", - "description": "The generated text response from the model" - }, - "usage": { - "type": "object", - "description": "Usage statistics for the inference request", - "properties": { - "prompt_tokens": { - "type": "number", - "description": "Total number of tokens in input", - "default": 0 - }, - "completion_tokens": { - "type": "number", - "description": "Total number of tokens in output", - "default": 0 - }, - "total_tokens": { - "type": "number", - "description": "Total number of input and output tokens", - "default": 0 - } - } - }, - "tool_calls": { - "type": "array", - "description": "An array of tool calls requests made during the response generation", - "items": { - "type": "object", - "properties": { - "arguments": { - "type": "object", - "description": "The arguments passed to be passed to the tool call request" - }, - "name": { - "type": "string", - "description": "The name of the tool to be called" - } - } - } - } - }, - "required": [ - "response" - ] - }, - { - "type": "string", - "format": "binary" - } - ] - } - } -} \ No newline at end of file diff --git a/src/content/workers-ai-models/openchat-3.5-0106.json b/src/content/workers-ai-models/openchat-3.5-0106.json deleted file mode 100644 index d1c026063962058..000000000000000 --- a/src/content/workers-ai-models/openchat-3.5-0106.json +++ /dev/null @@ -1,466 +0,0 @@ -{ - "id": "081054cd-a254-4349-855e-6dc0996277fa", - "source": 1, - "name": "@cf/openchat/openchat-3.5-0106", - "description": "OpenChat is an innovative library of open-source language models, fine-tuned with C-RLFT - a strategy inspired by offline reinforcement learning.", - "task": { - "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", - "name": "Text Generation", - "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." - }, - "created_at": "2024-02-27 18:20:39.169", - "tags": [], - "properties": [ - { - "property_id": "beta", - "value": "true" - }, - { - "property_id": "context_window", - "value": "8192" - }, - { - "property_id": "info", - "value": "https://huggingface.co/openchat/openchat-3.5-0106" - }, - { - "property_id": "planned_deprecation_date", - "value": "2025-10-01" - } - ], - "schema": { - "input": { - "type": "object", - "oneOf": [ - { - "title": "Prompt", - "properties": { - "prompt": { - "type": "string", - "minLength": 1, - "description": "The input text prompt for the model to generate a response." - }, - "lora": { - "type": "string", - "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." - }, - "response_format": { - "title": "JSON Mode", - "type": "object", - "properties": { - "type": { - "type": "string", - "enum": [ - "json_object", - "json_schema" - ] - }, - "json_schema": {} - } - }, - "raw": { - "type": "boolean", - "default": false, - "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." - }, - "stream": { - "type": "boolean", - "default": false, - "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." - }, - "max_tokens": { - "type": "integer", - "default": 256, - "description": "The maximum number of tokens to generate in the response." - }, - "temperature": { - "type": "number", - "default": 0.6, - "minimum": 0, - "maximum": 5, - "description": "Controls the randomness of the output; higher values produce more random results." - }, - "top_p": { - "type": "number", - "minimum": 0.001, - "maximum": 1, - "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." - }, - "top_k": { - "type": "integer", - "minimum": 1, - "maximum": 50, - "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." - }, - "seed": { - "type": "integer", - "minimum": 1, - "maximum": 9999999999, - "description": "Random seed for reproducibility of the generation." - }, - "repetition_penalty": { - "type": "number", - "minimum": 0, - "maximum": 2, - "description": "Penalty for repeated tokens; higher values discourage repetition." - }, - "frequency_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Decreases the likelihood of the model repeating the same lines verbatim." - }, - "presence_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Increases the likelihood of the model introducing new topics." - } - }, - "required": [ - "prompt" - ] - }, - { - "title": "Messages", - "properties": { - "messages": { - "type": "array", - "description": "An array of message objects representing the conversation history.", - "items": { - "type": "object", - "properties": { - "role": { - "type": "string", - "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." - }, - "content": { - "oneOf": [ - { - "type": "string", - "description": "The content of the message as a string." - }, - { - "type": "array", - "description": "Array of text content parts.", - "items": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "Type of the content (text)" - }, - "text": { - "type": "string", - "description": "Text content" - } - } - } - } - ] - } - }, - "required": [ - "role", - "content" - ] - } - }, - "functions": { - "type": "array", - "items": { - "type": "object", - "properties": { - "name": { - "type": "string" - }, - "code": { - "type": "string" - } - }, - "required": [ - "name", - "code" - ] - } - }, - "tools": { - "type": "array", - "description": "A list of tools available for the assistant to use.", - "items": { - "type": "object", - "oneOf": [ - { - "properties": { - "name": { - "type": "string", - "description": "The name of the tool. More descriptive the better." - }, - "description": { - "type": "string", - "description": "A brief description of what the tool does." - }, - "parameters": { - "type": "object", - "description": "Schema defining the parameters accepted by the tool.", - "properties": { - "type": { - "type": "string", - "description": "The type of the parameters object (usually 'object')." - }, - "required": { - "type": "array", - "description": "List of required parameter names.", - "items": { - "type": "string" - } - }, - "properties": { - "type": "object", - "description": "Definitions of each parameter.", - "additionalProperties": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "The data type of the parameter." - }, - "description": { - "type": "string", - "description": "A description of the expected parameter." - } - }, - "required": [ - "type", - "description" - ] - } - } - }, - "required": [ - "type", - "properties" - ] - } - }, - "required": [ - "name", - "description", - "parameters" - ] - }, - { - "properties": { - "type": { - "type": "string", - "description": "Specifies the type of tool (e.g., 'function')." - }, - "function": { - "type": "object", - "description": "Details of the function tool.", - "properties": { - "name": { - "type": "string", - "description": "The name of the function." - }, - "description": { - "type": "string", - "description": "A brief description of what the function does." - }, - "parameters": { - "type": "object", - "description": "Schema defining the parameters accepted by the function.", - "properties": { - "type": { - "type": "string", - "description": "The type of the parameters object (usually 'object')." - }, - "required": { - "type": "array", - "description": "List of required parameter names.", - "items": { - "type": "string" - } - }, - "properties": { - "type": "object", - "description": "Definitions of each parameter.", - "additionalProperties": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "The data type of the parameter." - }, - "description": { - "type": "string", - "description": "A description of the expected parameter." - } - }, - "required": [ - "type", - "description" - ] - } - } - }, - "required": [ - "type", - "properties" - ] - } - }, - "required": [ - "name", - "description", - "parameters" - ] - } - }, - "required": [ - "type", - "function" - ] - } - ] - } - }, - "response_format": { - "title": "JSON Mode", - "type": "object", - "properties": { - "type": { - "type": "string", - "enum": [ - "json_object", - "json_schema" - ] - }, - "json_schema": {} - } - }, - "raw": { - "type": "boolean", - "default": false, - "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." - }, - "stream": { - "type": "boolean", - "default": false, - "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." - }, - "max_tokens": { - "type": "integer", - "default": 256, - "description": "The maximum number of tokens to generate in the response." - }, - "temperature": { - "type": "number", - "default": 0.6, - "minimum": 0, - "maximum": 5, - "description": "Controls the randomness of the output; higher values produce more random results." - }, - "top_p": { - "type": "number", - "minimum": 0.001, - "maximum": 1, - "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." - }, - "top_k": { - "type": "integer", - "minimum": 1, - "maximum": 50, - "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." - }, - "seed": { - "type": "integer", - "minimum": 1, - "maximum": 9999999999, - "description": "Random seed for reproducibility of the generation." - }, - "repetition_penalty": { - "type": "number", - "minimum": 0, - "maximum": 2, - "description": "Penalty for repeated tokens; higher values discourage repetition." - }, - "frequency_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Decreases the likelihood of the model repeating the same lines verbatim." - }, - "presence_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Increases the likelihood of the model introducing new topics." - } - }, - "required": [ - "messages" - ] - } - ] - }, - "output": { - "oneOf": [ - { - "type": "object", - "properties": { - "response": { - "type": "string", - "description": "The generated text response from the model" - }, - "usage": { - "type": "object", - "description": "Usage statistics for the inference request", - "properties": { - "prompt_tokens": { - "type": "number", - "description": "Total number of tokens in input", - "default": 0 - }, - "completion_tokens": { - "type": "number", - "description": "Total number of tokens in output", - "default": 0 - }, - "total_tokens": { - "type": "number", - "description": "Total number of input and output tokens", - "default": 0 - } - } - }, - "tool_calls": { - "type": "array", - "description": "An array of tool calls requests made during the response generation", - "items": { - "type": "object", - "properties": { - "arguments": { - "type": "object", - "description": "The arguments passed to be passed to the tool call request" - }, - "name": { - "type": "string", - "description": "The name of the tool to be called" - } - } - } - } - }, - "required": [ - "response" - ] - }, - { - "type": "string", - "format": "binary" - } - ] - } - } -} \ No newline at end of file diff --git a/src/content/workers-ai-models/openhermes-2.5-mistral-7b-awq.json b/src/content/workers-ai-models/openhermes-2.5-mistral-7b-awq.json deleted file mode 100644 index 829f9c50a7847a2..000000000000000 --- a/src/content/workers-ai-models/openhermes-2.5-mistral-7b-awq.json +++ /dev/null @@ -1,462 +0,0 @@ -{ - "id": "673c56cc-8553-49a1-b179-dd549ec9209a", - "source": 2, - "name": "@hf/thebloke/openhermes-2.5-mistral-7b-awq", - "description": "OpenHermes 2.5 Mistral 7B is a state of the art Mistral Fine-tune, a continuation of OpenHermes 2 model, which trained on additional code datasets.", - "task": { - "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", - "name": "Text Generation", - "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." - }, - "created_at": "2024-02-06 18:04:22.846", - "tags": [], - "properties": [ - { - "property_id": "beta", - "value": "true" - }, - { - "property_id": "context_window", - "value": "4096" - }, - { - "property_id": "planned_deprecation_date", - "value": "2025-10-01" - } - ], - "schema": { - "input": { - "type": "object", - "oneOf": [ - { - "title": "Prompt", - "properties": { - "prompt": { - "type": "string", - "minLength": 1, - "description": "The input text prompt for the model to generate a response." - }, - "lora": { - "type": "string", - "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." - }, - "response_format": { - "title": "JSON Mode", - "type": "object", - "properties": { - "type": { - "type": "string", - "enum": [ - "json_object", - "json_schema" - ] - }, - "json_schema": {} - } - }, - "raw": { - "type": "boolean", - "default": false, - "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." - }, - "stream": { - "type": "boolean", - "default": false, - "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." - }, - "max_tokens": { - "type": "integer", - "default": 256, - "description": "The maximum number of tokens to generate in the response." - }, - "temperature": { - "type": "number", - "default": 0.6, - "minimum": 0, - "maximum": 5, - "description": "Controls the randomness of the output; higher values produce more random results." - }, - "top_p": { - "type": "number", - "minimum": 0.001, - "maximum": 1, - "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." - }, - "top_k": { - "type": "integer", - "minimum": 1, - "maximum": 50, - "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." - }, - "seed": { - "type": "integer", - "minimum": 1, - "maximum": 9999999999, - "description": "Random seed for reproducibility of the generation." - }, - "repetition_penalty": { - "type": "number", - "minimum": 0, - "maximum": 2, - "description": "Penalty for repeated tokens; higher values discourage repetition." - }, - "frequency_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Decreases the likelihood of the model repeating the same lines verbatim." - }, - "presence_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Increases the likelihood of the model introducing new topics." - } - }, - "required": [ - "prompt" - ] - }, - { - "title": "Messages", - "properties": { - "messages": { - "type": "array", - "description": "An array of message objects representing the conversation history.", - "items": { - "type": "object", - "properties": { - "role": { - "type": "string", - "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." - }, - "content": { - "oneOf": [ - { - "type": "string", - "description": "The content of the message as a string." - }, - { - "type": "array", - "description": "Array of text content parts.", - "items": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "Type of the content (text)" - }, - "text": { - "type": "string", - "description": "Text content" - } - } - } - } - ] - } - }, - "required": [ - "role", - "content" - ] - } - }, - "functions": { - "type": "array", - "items": { - "type": "object", - "properties": { - "name": { - "type": "string" - }, - "code": { - "type": "string" - } - }, - "required": [ - "name", - "code" - ] - } - }, - "tools": { - "type": "array", - "description": "A list of tools available for the assistant to use.", - "items": { - "type": "object", - "oneOf": [ - { - "properties": { - "name": { - "type": "string", - "description": "The name of the tool. More descriptive the better." - }, - "description": { - "type": "string", - "description": "A brief description of what the tool does." - }, - "parameters": { - "type": "object", - "description": "Schema defining the parameters accepted by the tool.", - "properties": { - "type": { - "type": "string", - "description": "The type of the parameters object (usually 'object')." - }, - "required": { - "type": "array", - "description": "List of required parameter names.", - "items": { - "type": "string" - } - }, - "properties": { - "type": "object", - "description": "Definitions of each parameter.", - "additionalProperties": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "The data type of the parameter." - }, - "description": { - "type": "string", - "description": "A description of the expected parameter." - } - }, - "required": [ - "type", - "description" - ] - } - } - }, - "required": [ - "type", - "properties" - ] - } - }, - "required": [ - "name", - "description", - "parameters" - ] - }, - { - "properties": { - "type": { - "type": "string", - "description": "Specifies the type of tool (e.g., 'function')." - }, - "function": { - "type": "object", - "description": "Details of the function tool.", - "properties": { - "name": { - "type": "string", - "description": "The name of the function." - }, - "description": { - "type": "string", - "description": "A brief description of what the function does." - }, - "parameters": { - "type": "object", - "description": "Schema defining the parameters accepted by the function.", - "properties": { - "type": { - "type": "string", - "description": "The type of the parameters object (usually 'object')." - }, - "required": { - "type": "array", - "description": "List of required parameter names.", - "items": { - "type": "string" - } - }, - "properties": { - "type": "object", - "description": "Definitions of each parameter.", - "additionalProperties": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "The data type of the parameter." - }, - "description": { - "type": "string", - "description": "A description of the expected parameter." - } - }, - "required": [ - "type", - "description" - ] - } - } - }, - "required": [ - "type", - "properties" - ] - } - }, - "required": [ - "name", - "description", - "parameters" - ] - } - }, - "required": [ - "type", - "function" - ] - } - ] - } - }, - "response_format": { - "title": "JSON Mode", - "type": "object", - "properties": { - "type": { - "type": "string", - "enum": [ - "json_object", - "json_schema" - ] - }, - "json_schema": {} - } - }, - "raw": { - "type": "boolean", - "default": false, - "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." - }, - "stream": { - "type": "boolean", - "default": false, - "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." - }, - "max_tokens": { - "type": "integer", - "default": 256, - "description": "The maximum number of tokens to generate in the response." - }, - "temperature": { - "type": "number", - "default": 0.6, - "minimum": 0, - "maximum": 5, - "description": "Controls the randomness of the output; higher values produce more random results." - }, - "top_p": { - "type": "number", - "minimum": 0.001, - "maximum": 1, - "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." - }, - "top_k": { - "type": "integer", - "minimum": 1, - "maximum": 50, - "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." - }, - "seed": { - "type": "integer", - "minimum": 1, - "maximum": 9999999999, - "description": "Random seed for reproducibility of the generation." - }, - "repetition_penalty": { - "type": "number", - "minimum": 0, - "maximum": 2, - "description": "Penalty for repeated tokens; higher values discourage repetition." - }, - "frequency_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Decreases the likelihood of the model repeating the same lines verbatim." - }, - "presence_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Increases the likelihood of the model introducing new topics." - } - }, - "required": [ - "messages" - ] - } - ] - }, - "output": { - "oneOf": [ - { - "type": "object", - "properties": { - "response": { - "type": "string", - "description": "The generated text response from the model" - }, - "usage": { - "type": "object", - "description": "Usage statistics for the inference request", - "properties": { - "prompt_tokens": { - "type": "number", - "description": "Total number of tokens in input", - "default": 0 - }, - "completion_tokens": { - "type": "number", - "description": "Total number of tokens in output", - "default": 0 - }, - "total_tokens": { - "type": "number", - "description": "Total number of input and output tokens", - "default": 0 - } - } - }, - "tool_calls": { - "type": "array", - "description": "An array of tool calls requests made during the response generation", - "items": { - "type": "object", - "properties": { - "arguments": { - "type": "object", - "description": "The arguments passed to be passed to the tool call request" - }, - "name": { - "type": "string", - "description": "The name of the tool to be called" - } - } - } - } - }, - "required": [ - "response" - ] - }, - { - "type": "string", - "format": "binary" - } - ] - } - } -} \ No newline at end of file diff --git a/src/content/workers-ai-models/qwen1.5-0.5b-chat.json b/src/content/workers-ai-models/qwen1.5-0.5b-chat.json deleted file mode 100644 index 1ea2d8b7cd48e7d..000000000000000 --- a/src/content/workers-ai-models/qwen1.5-0.5b-chat.json +++ /dev/null @@ -1,466 +0,0 @@ -{ - "id": "f8703a00-ed54-4f98-bdc3-cd9a813286f3", - "source": 1, - "name": "@cf/qwen/qwen1.5-0.5b-chat", - "description": "Qwen1.5 is the improved version of Qwen, the large language model series developed by Alibaba Cloud.", - "task": { - "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", - "name": "Text Generation", - "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." - }, - "created_at": "2024-02-27 18:23:37.344", - "tags": [], - "properties": [ - { - "property_id": "beta", - "value": "true" - }, - { - "property_id": "context_window", - "value": "32000" - }, - { - "property_id": "info", - "value": "https://huggingface.co/qwen/qwen1.5-0.5b-chat" - }, - { - "property_id": "planned_deprecation_date", - "value": "2025-10-01" - } - ], - "schema": { - "input": { - "type": "object", - "oneOf": [ - { - "title": "Prompt", - "properties": { - "prompt": { - "type": "string", - "minLength": 1, - "description": "The input text prompt for the model to generate a response." - }, - "lora": { - "type": "string", - "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." - }, - "response_format": { - "title": "JSON Mode", - "type": "object", - "properties": { - "type": { - "type": "string", - "enum": [ - "json_object", - "json_schema" - ] - }, - "json_schema": {} - } - }, - "raw": { - "type": "boolean", - "default": false, - "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." - }, - "stream": { - "type": "boolean", - "default": false, - "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." - }, - "max_tokens": { - "type": "integer", - "default": 256, - "description": "The maximum number of tokens to generate in the response." - }, - "temperature": { - "type": "number", - "default": 0.6, - "minimum": 0, - "maximum": 5, - "description": "Controls the randomness of the output; higher values produce more random results." - }, - "top_p": { - "type": "number", - "minimum": 0.001, - "maximum": 1, - "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." - }, - "top_k": { - "type": "integer", - "minimum": 1, - "maximum": 50, - "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." - }, - "seed": { - "type": "integer", - "minimum": 1, - "maximum": 9999999999, - "description": "Random seed for reproducibility of the generation." - }, - "repetition_penalty": { - "type": "number", - "minimum": 0, - "maximum": 2, - "description": "Penalty for repeated tokens; higher values discourage repetition." - }, - "frequency_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Decreases the likelihood of the model repeating the same lines verbatim." - }, - "presence_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Increases the likelihood of the model introducing new topics." - } - }, - "required": [ - "prompt" - ] - }, - { - "title": "Messages", - "properties": { - "messages": { - "type": "array", - "description": "An array of message objects representing the conversation history.", - "items": { - "type": "object", - "properties": { - "role": { - "type": "string", - "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." - }, - "content": { - "oneOf": [ - { - "type": "string", - "description": "The content of the message as a string." - }, - { - "type": "array", - "description": "Array of text content parts.", - "items": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "Type of the content (text)" - }, - "text": { - "type": "string", - "description": "Text content" - } - } - } - } - ] - } - }, - "required": [ - "role", - "content" - ] - } - }, - "functions": { - "type": "array", - "items": { - "type": "object", - "properties": { - "name": { - "type": "string" - }, - "code": { - "type": "string" - } - }, - "required": [ - "name", - "code" - ] - } - }, - "tools": { - "type": "array", - "description": "A list of tools available for the assistant to use.", - "items": { - "type": "object", - "oneOf": [ - { - "properties": { - "name": { - "type": "string", - "description": "The name of the tool. More descriptive the better." - }, - "description": { - "type": "string", - "description": "A brief description of what the tool does." - }, - "parameters": { - "type": "object", - "description": "Schema defining the parameters accepted by the tool.", - "properties": { - "type": { - "type": "string", - "description": "The type of the parameters object (usually 'object')." - }, - "required": { - "type": "array", - "description": "List of required parameter names.", - "items": { - "type": "string" - } - }, - "properties": { - "type": "object", - "description": "Definitions of each parameter.", - "additionalProperties": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "The data type of the parameter." - }, - "description": { - "type": "string", - "description": "A description of the expected parameter." - } - }, - "required": [ - "type", - "description" - ] - } - } - }, - "required": [ - "type", - "properties" - ] - } - }, - "required": [ - "name", - "description", - "parameters" - ] - }, - { - "properties": { - "type": { - "type": "string", - "description": "Specifies the type of tool (e.g., 'function')." - }, - "function": { - "type": "object", - "description": "Details of the function tool.", - "properties": { - "name": { - "type": "string", - "description": "The name of the function." - }, - "description": { - "type": "string", - "description": "A brief description of what the function does." - }, - "parameters": { - "type": "object", - "description": "Schema defining the parameters accepted by the function.", - "properties": { - "type": { - "type": "string", - "description": "The type of the parameters object (usually 'object')." - }, - "required": { - "type": "array", - "description": "List of required parameter names.", - "items": { - "type": "string" - } - }, - "properties": { - "type": "object", - "description": "Definitions of each parameter.", - "additionalProperties": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "The data type of the parameter." - }, - "description": { - "type": "string", - "description": "A description of the expected parameter." - } - }, - "required": [ - "type", - "description" - ] - } - } - }, - "required": [ - "type", - "properties" - ] - } - }, - "required": [ - "name", - "description", - "parameters" - ] - } - }, - "required": [ - "type", - "function" - ] - } - ] - } - }, - "response_format": { - "title": "JSON Mode", - "type": "object", - "properties": { - "type": { - "type": "string", - "enum": [ - "json_object", - "json_schema" - ] - }, - "json_schema": {} - } - }, - "raw": { - "type": "boolean", - "default": false, - "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." - }, - "stream": { - "type": "boolean", - "default": false, - "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." - }, - "max_tokens": { - "type": "integer", - "default": 256, - "description": "The maximum number of tokens to generate in the response." - }, - "temperature": { - "type": "number", - "default": 0.6, - "minimum": 0, - "maximum": 5, - "description": "Controls the randomness of the output; higher values produce more random results." - }, - "top_p": { - "type": "number", - "minimum": 0.001, - "maximum": 1, - "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." - }, - "top_k": { - "type": "integer", - "minimum": 1, - "maximum": 50, - "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." - }, - "seed": { - "type": "integer", - "minimum": 1, - "maximum": 9999999999, - "description": "Random seed for reproducibility of the generation." - }, - "repetition_penalty": { - "type": "number", - "minimum": 0, - "maximum": 2, - "description": "Penalty for repeated tokens; higher values discourage repetition." - }, - "frequency_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Decreases the likelihood of the model repeating the same lines verbatim." - }, - "presence_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Increases the likelihood of the model introducing new topics." - } - }, - "required": [ - "messages" - ] - } - ] - }, - "output": { - "oneOf": [ - { - "type": "object", - "properties": { - "response": { - "type": "string", - "description": "The generated text response from the model" - }, - "usage": { - "type": "object", - "description": "Usage statistics for the inference request", - "properties": { - "prompt_tokens": { - "type": "number", - "description": "Total number of tokens in input", - "default": 0 - }, - "completion_tokens": { - "type": "number", - "description": "Total number of tokens in output", - "default": 0 - }, - "total_tokens": { - "type": "number", - "description": "Total number of input and output tokens", - "default": 0 - } - } - }, - "tool_calls": { - "type": "array", - "description": "An array of tool calls requests made during the response generation", - "items": { - "type": "object", - "properties": { - "arguments": { - "type": "object", - "description": "The arguments passed to be passed to the tool call request" - }, - "name": { - "type": "string", - "description": "The name of the tool to be called" - } - } - } - } - }, - "required": [ - "response" - ] - }, - { - "type": "string", - "format": "binary" - } - ] - } - } -} \ No newline at end of file diff --git a/src/content/workers-ai-models/qwen1.5-1.8b-chat.json b/src/content/workers-ai-models/qwen1.5-1.8b-chat.json deleted file mode 100644 index 77e068ff429ef04..000000000000000 --- a/src/content/workers-ai-models/qwen1.5-1.8b-chat.json +++ /dev/null @@ -1,466 +0,0 @@ -{ - "id": "3222ddb3-e211-4fd9-9a6d-79a80e47b3a6", - "source": 1, - "name": "@cf/qwen/qwen1.5-1.8b-chat", - "description": "Qwen1.5 is the improved version of Qwen, the large language model series developed by Alibaba Cloud.", - "task": { - "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", - "name": "Text Generation", - "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." - }, - "created_at": "2024-02-27 18:30:31.723", - "tags": [], - "properties": [ - { - "property_id": "beta", - "value": "true" - }, - { - "property_id": "context_window", - "value": "32000" - }, - { - "property_id": "info", - "value": "https://huggingface.co/qwen/qwen1.5-1.8b-chat" - }, - { - "property_id": "planned_deprecation_date", - "value": "2025-10-01" - } - ], - "schema": { - "input": { - "type": "object", - "oneOf": [ - { - "title": "Prompt", - "properties": { - "prompt": { - "type": "string", - "minLength": 1, - "description": "The input text prompt for the model to generate a response." - }, - "lora": { - "type": "string", - "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." - }, - "response_format": { - "title": "JSON Mode", - "type": "object", - "properties": { - "type": { - "type": "string", - "enum": [ - "json_object", - "json_schema" - ] - }, - "json_schema": {} - } - }, - "raw": { - "type": "boolean", - "default": false, - "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." - }, - "stream": { - "type": "boolean", - "default": false, - "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." - }, - "max_tokens": { - "type": "integer", - "default": 256, - "description": "The maximum number of tokens to generate in the response." - }, - "temperature": { - "type": "number", - "default": 0.6, - "minimum": 0, - "maximum": 5, - "description": "Controls the randomness of the output; higher values produce more random results." - }, - "top_p": { - "type": "number", - "minimum": 0.001, - "maximum": 1, - "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." - }, - "top_k": { - "type": "integer", - "minimum": 1, - "maximum": 50, - "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." - }, - "seed": { - "type": "integer", - "minimum": 1, - "maximum": 9999999999, - "description": "Random seed for reproducibility of the generation." - }, - "repetition_penalty": { - "type": "number", - "minimum": 0, - "maximum": 2, - "description": "Penalty for repeated tokens; higher values discourage repetition." - }, - "frequency_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Decreases the likelihood of the model repeating the same lines verbatim." - }, - "presence_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Increases the likelihood of the model introducing new topics." - } - }, - "required": [ - "prompt" - ] - }, - { - "title": "Messages", - "properties": { - "messages": { - "type": "array", - "description": "An array of message objects representing the conversation history.", - "items": { - "type": "object", - "properties": { - "role": { - "type": "string", - "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." - }, - "content": { - "oneOf": [ - { - "type": "string", - "description": "The content of the message as a string." - }, - { - "type": "array", - "description": "Array of text content parts.", - "items": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "Type of the content (text)" - }, - "text": { - "type": "string", - "description": "Text content" - } - } - } - } - ] - } - }, - "required": [ - "role", - "content" - ] - } - }, - "functions": { - "type": "array", - "items": { - "type": "object", - "properties": { - "name": { - "type": "string" - }, - "code": { - "type": "string" - } - }, - "required": [ - "name", - "code" - ] - } - }, - "tools": { - "type": "array", - "description": "A list of tools available for the assistant to use.", - "items": { - "type": "object", - "oneOf": [ - { - "properties": { - "name": { - "type": "string", - "description": "The name of the tool. More descriptive the better." - }, - "description": { - "type": "string", - "description": "A brief description of what the tool does." - }, - "parameters": { - "type": "object", - "description": "Schema defining the parameters accepted by the tool.", - "properties": { - "type": { - "type": "string", - "description": "The type of the parameters object (usually 'object')." - }, - "required": { - "type": "array", - "description": "List of required parameter names.", - "items": { - "type": "string" - } - }, - "properties": { - "type": "object", - "description": "Definitions of each parameter.", - "additionalProperties": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "The data type of the parameter." - }, - "description": { - "type": "string", - "description": "A description of the expected parameter." - } - }, - "required": [ - "type", - "description" - ] - } - } - }, - "required": [ - "type", - "properties" - ] - } - }, - "required": [ - "name", - "description", - "parameters" - ] - }, - { - "properties": { - "type": { - "type": "string", - "description": "Specifies the type of tool (e.g., 'function')." - }, - "function": { - "type": "object", - "description": "Details of the function tool.", - "properties": { - "name": { - "type": "string", - "description": "The name of the function." - }, - "description": { - "type": "string", - "description": "A brief description of what the function does." - }, - "parameters": { - "type": "object", - "description": "Schema defining the parameters accepted by the function.", - "properties": { - "type": { - "type": "string", - "description": "The type of the parameters object (usually 'object')." - }, - "required": { - "type": "array", - "description": "List of required parameter names.", - "items": { - "type": "string" - } - }, - "properties": { - "type": "object", - "description": "Definitions of each parameter.", - "additionalProperties": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "The data type of the parameter." - }, - "description": { - "type": "string", - "description": "A description of the expected parameter." - } - }, - "required": [ - "type", - "description" - ] - } - } - }, - "required": [ - "type", - "properties" - ] - } - }, - "required": [ - "name", - "description", - "parameters" - ] - } - }, - "required": [ - "type", - "function" - ] - } - ] - } - }, - "response_format": { - "title": "JSON Mode", - "type": "object", - "properties": { - "type": { - "type": "string", - "enum": [ - "json_object", - "json_schema" - ] - }, - "json_schema": {} - } - }, - "raw": { - "type": "boolean", - "default": false, - "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." - }, - "stream": { - "type": "boolean", - "default": false, - "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." - }, - "max_tokens": { - "type": "integer", - "default": 256, - "description": "The maximum number of tokens to generate in the response." - }, - "temperature": { - "type": "number", - "default": 0.6, - "minimum": 0, - "maximum": 5, - "description": "Controls the randomness of the output; higher values produce more random results." - }, - "top_p": { - "type": "number", - "minimum": 0.001, - "maximum": 1, - "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." - }, - "top_k": { - "type": "integer", - "minimum": 1, - "maximum": 50, - "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." - }, - "seed": { - "type": "integer", - "minimum": 1, - "maximum": 9999999999, - "description": "Random seed for reproducibility of the generation." - }, - "repetition_penalty": { - "type": "number", - "minimum": 0, - "maximum": 2, - "description": "Penalty for repeated tokens; higher values discourage repetition." - }, - "frequency_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Decreases the likelihood of the model repeating the same lines verbatim." - }, - "presence_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Increases the likelihood of the model introducing new topics." - } - }, - "required": [ - "messages" - ] - } - ] - }, - "output": { - "oneOf": [ - { - "type": "object", - "properties": { - "response": { - "type": "string", - "description": "The generated text response from the model" - }, - "usage": { - "type": "object", - "description": "Usage statistics for the inference request", - "properties": { - "prompt_tokens": { - "type": "number", - "description": "Total number of tokens in input", - "default": 0 - }, - "completion_tokens": { - "type": "number", - "description": "Total number of tokens in output", - "default": 0 - }, - "total_tokens": { - "type": "number", - "description": "Total number of input and output tokens", - "default": 0 - } - } - }, - "tool_calls": { - "type": "array", - "description": "An array of tool calls requests made during the response generation", - "items": { - "type": "object", - "properties": { - "arguments": { - "type": "object", - "description": "The arguments passed to be passed to the tool call request" - }, - "name": { - "type": "string", - "description": "The name of the tool to be called" - } - } - } - } - }, - "required": [ - "response" - ] - }, - { - "type": "string", - "format": "binary" - } - ] - } - } -} \ No newline at end of file diff --git a/src/content/workers-ai-models/qwen1.5-14b-chat-awq.json b/src/content/workers-ai-models/qwen1.5-14b-chat-awq.json deleted file mode 100644 index c51f1b9265e0f11..000000000000000 --- a/src/content/workers-ai-models/qwen1.5-14b-chat-awq.json +++ /dev/null @@ -1,466 +0,0 @@ -{ - "id": "09d113a9-03c4-420e-b6f2-52ad4b3bed45", - "source": 1, - "name": "@cf/qwen/qwen1.5-14b-chat-awq", - "description": "Qwen1.5 is the improved version of Qwen, the large language model series developed by Alibaba Cloud. AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization.", - "task": { - "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", - "name": "Text Generation", - "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." - }, - "created_at": "2024-02-27 18:24:45.316", - "tags": [], - "properties": [ - { - "property_id": "beta", - "value": "true" - }, - { - "property_id": "context_window", - "value": "7500" - }, - { - "property_id": "info", - "value": "https://huggingface.co/qwen/qwen1.5-14b-chat-awq" - }, - { - "property_id": "planned_deprecation_date", - "value": "2025-10-01" - } - ], - "schema": { - "input": { - "type": "object", - "oneOf": [ - { - "title": "Prompt", - "properties": { - "prompt": { - "type": "string", - "minLength": 1, - "description": "The input text prompt for the model to generate a response." - }, - "lora": { - "type": "string", - "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." - }, - "response_format": { - "title": "JSON Mode", - "type": "object", - "properties": { - "type": { - "type": "string", - "enum": [ - "json_object", - "json_schema" - ] - }, - "json_schema": {} - } - }, - "raw": { - "type": "boolean", - "default": false, - "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." - }, - "stream": { - "type": "boolean", - "default": false, - "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." - }, - "max_tokens": { - "type": "integer", - "default": 256, - "description": "The maximum number of tokens to generate in the response." - }, - "temperature": { - "type": "number", - "default": 0.6, - "minimum": 0, - "maximum": 5, - "description": "Controls the randomness of the output; higher values produce more random results." - }, - "top_p": { - "type": "number", - "minimum": 0.001, - "maximum": 1, - "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." - }, - "top_k": { - "type": "integer", - "minimum": 1, - "maximum": 50, - "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." - }, - "seed": { - "type": "integer", - "minimum": 1, - "maximum": 9999999999, - "description": "Random seed for reproducibility of the generation." - }, - "repetition_penalty": { - "type": "number", - "minimum": 0, - "maximum": 2, - "description": "Penalty for repeated tokens; higher values discourage repetition." - }, - "frequency_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Decreases the likelihood of the model repeating the same lines verbatim." - }, - "presence_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Increases the likelihood of the model introducing new topics." - } - }, - "required": [ - "prompt" - ] - }, - { - "title": "Messages", - "properties": { - "messages": { - "type": "array", - "description": "An array of message objects representing the conversation history.", - "items": { - "type": "object", - "properties": { - "role": { - "type": "string", - "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." - }, - "content": { - "oneOf": [ - { - "type": "string", - "description": "The content of the message as a string." - }, - { - "type": "array", - "description": "Array of text content parts.", - "items": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "Type of the content (text)" - }, - "text": { - "type": "string", - "description": "Text content" - } - } - } - } - ] - } - }, - "required": [ - "role", - "content" - ] - } - }, - "functions": { - "type": "array", - "items": { - "type": "object", - "properties": { - "name": { - "type": "string" - }, - "code": { - "type": "string" - } - }, - "required": [ - "name", - "code" - ] - } - }, - "tools": { - "type": "array", - "description": "A list of tools available for the assistant to use.", - "items": { - "type": "object", - "oneOf": [ - { - "properties": { - "name": { - "type": "string", - "description": "The name of the tool. More descriptive the better." - }, - "description": { - "type": "string", - "description": "A brief description of what the tool does." - }, - "parameters": { - "type": "object", - "description": "Schema defining the parameters accepted by the tool.", - "properties": { - "type": { - "type": "string", - "description": "The type of the parameters object (usually 'object')." - }, - "required": { - "type": "array", - "description": "List of required parameter names.", - "items": { - "type": "string" - } - }, - "properties": { - "type": "object", - "description": "Definitions of each parameter.", - "additionalProperties": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "The data type of the parameter." - }, - "description": { - "type": "string", - "description": "A description of the expected parameter." - } - }, - "required": [ - "type", - "description" - ] - } - } - }, - "required": [ - "type", - "properties" - ] - } - }, - "required": [ - "name", - "description", - "parameters" - ] - }, - { - "properties": { - "type": { - "type": "string", - "description": "Specifies the type of tool (e.g., 'function')." - }, - "function": { - "type": "object", - "description": "Details of the function tool.", - "properties": { - "name": { - "type": "string", - "description": "The name of the function." - }, - "description": { - "type": "string", - "description": "A brief description of what the function does." - }, - "parameters": { - "type": "object", - "description": "Schema defining the parameters accepted by the function.", - "properties": { - "type": { - "type": "string", - "description": "The type of the parameters object (usually 'object')." - }, - "required": { - "type": "array", - "description": "List of required parameter names.", - "items": { - "type": "string" - } - }, - "properties": { - "type": "object", - "description": "Definitions of each parameter.", - "additionalProperties": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "The data type of the parameter." - }, - "description": { - "type": "string", - "description": "A description of the expected parameter." - } - }, - "required": [ - "type", - "description" - ] - } - } - }, - "required": [ - "type", - "properties" - ] - } - }, - "required": [ - "name", - "description", - "parameters" - ] - } - }, - "required": [ - "type", - "function" - ] - } - ] - } - }, - "response_format": { - "title": "JSON Mode", - "type": "object", - "properties": { - "type": { - "type": "string", - "enum": [ - "json_object", - "json_schema" - ] - }, - "json_schema": {} - } - }, - "raw": { - "type": "boolean", - "default": false, - "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." - }, - "stream": { - "type": "boolean", - "default": false, - "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." - }, - "max_tokens": { - "type": "integer", - "default": 256, - "description": "The maximum number of tokens to generate in the response." - }, - "temperature": { - "type": "number", - "default": 0.6, - "minimum": 0, - "maximum": 5, - "description": "Controls the randomness of the output; higher values produce more random results." - }, - "top_p": { - "type": "number", - "minimum": 0.001, - "maximum": 1, - "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." - }, - "top_k": { - "type": "integer", - "minimum": 1, - "maximum": 50, - "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." - }, - "seed": { - "type": "integer", - "minimum": 1, - "maximum": 9999999999, - "description": "Random seed for reproducibility of the generation." - }, - "repetition_penalty": { - "type": "number", - "minimum": 0, - "maximum": 2, - "description": "Penalty for repeated tokens; higher values discourage repetition." - }, - "frequency_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Decreases the likelihood of the model repeating the same lines verbatim." - }, - "presence_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Increases the likelihood of the model introducing new topics." - } - }, - "required": [ - "messages" - ] - } - ] - }, - "output": { - "oneOf": [ - { - "type": "object", - "properties": { - "response": { - "type": "string", - "description": "The generated text response from the model" - }, - "usage": { - "type": "object", - "description": "Usage statistics for the inference request", - "properties": { - "prompt_tokens": { - "type": "number", - "description": "Total number of tokens in input", - "default": 0 - }, - "completion_tokens": { - "type": "number", - "description": "Total number of tokens in output", - "default": 0 - }, - "total_tokens": { - "type": "number", - "description": "Total number of input and output tokens", - "default": 0 - } - } - }, - "tool_calls": { - "type": "array", - "description": "An array of tool calls requests made during the response generation", - "items": { - "type": "object", - "properties": { - "arguments": { - "type": "object", - "description": "The arguments passed to be passed to the tool call request" - }, - "name": { - "type": "string", - "description": "The name of the tool to be called" - } - } - } - } - }, - "required": [ - "response" - ] - }, - { - "type": "string", - "format": "binary" - } - ] - } - } -} \ No newline at end of file diff --git a/src/content/workers-ai-models/qwen1.5-7b-chat-awq.json b/src/content/workers-ai-models/qwen1.5-7b-chat-awq.json deleted file mode 100644 index ee17ba9abaeb0e4..000000000000000 --- a/src/content/workers-ai-models/qwen1.5-7b-chat-awq.json +++ /dev/null @@ -1,466 +0,0 @@ -{ - "id": "90a20ae7-7cf4-4eb3-8672-8fc4ee580635", - "source": 1, - "name": "@cf/qwen/qwen1.5-7b-chat-awq", - "description": "Qwen1.5 is the improved version of Qwen, the large language model series developed by Alibaba Cloud. AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization.", - "task": { - "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", - "name": "Text Generation", - "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." - }, - "created_at": "2024-02-27 18:24:11.709", - "tags": [], - "properties": [ - { - "property_id": "beta", - "value": "true" - }, - { - "property_id": "context_window", - "value": "20000" - }, - { - "property_id": "info", - "value": "https://huggingface.co/qwen/qwen1.5-7b-chat-awq" - }, - { - "property_id": "planned_deprecation_date", - "value": "2025-10-01" - } - ], - "schema": { - "input": { - "type": "object", - "oneOf": [ - { - "title": "Prompt", - "properties": { - "prompt": { - "type": "string", - "minLength": 1, - "description": "The input text prompt for the model to generate a response." - }, - "lora": { - "type": "string", - "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." - }, - "response_format": { - "title": "JSON Mode", - "type": "object", - "properties": { - "type": { - "type": "string", - "enum": [ - "json_object", - "json_schema" - ] - }, - "json_schema": {} - } - }, - "raw": { - "type": "boolean", - "default": false, - "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." - }, - "stream": { - "type": "boolean", - "default": false, - "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." - }, - "max_tokens": { - "type": "integer", - "default": 256, - "description": "The maximum number of tokens to generate in the response." - }, - "temperature": { - "type": "number", - "default": 0.6, - "minimum": 0, - "maximum": 5, - "description": "Controls the randomness of the output; higher values produce more random results." - }, - "top_p": { - "type": "number", - "minimum": 0.001, - "maximum": 1, - "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." - }, - "top_k": { - "type": "integer", - "minimum": 1, - "maximum": 50, - "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." - }, - "seed": { - "type": "integer", - "minimum": 1, - "maximum": 9999999999, - "description": "Random seed for reproducibility of the generation." - }, - "repetition_penalty": { - "type": "number", - "minimum": 0, - "maximum": 2, - "description": "Penalty for repeated tokens; higher values discourage repetition." - }, - "frequency_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Decreases the likelihood of the model repeating the same lines verbatim." - }, - "presence_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Increases the likelihood of the model introducing new topics." - } - }, - "required": [ - "prompt" - ] - }, - { - "title": "Messages", - "properties": { - "messages": { - "type": "array", - "description": "An array of message objects representing the conversation history.", - "items": { - "type": "object", - "properties": { - "role": { - "type": "string", - "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." - }, - "content": { - "oneOf": [ - { - "type": "string", - "description": "The content of the message as a string." - }, - { - "type": "array", - "description": "Array of text content parts.", - "items": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "Type of the content (text)" - }, - "text": { - "type": "string", - "description": "Text content" - } - } - } - } - ] - } - }, - "required": [ - "role", - "content" - ] - } - }, - "functions": { - "type": "array", - "items": { - "type": "object", - "properties": { - "name": { - "type": "string" - }, - "code": { - "type": "string" - } - }, - "required": [ - "name", - "code" - ] - } - }, - "tools": { - "type": "array", - "description": "A list of tools available for the assistant to use.", - "items": { - "type": "object", - "oneOf": [ - { - "properties": { - "name": { - "type": "string", - "description": "The name of the tool. More descriptive the better." - }, - "description": { - "type": "string", - "description": "A brief description of what the tool does." - }, - "parameters": { - "type": "object", - "description": "Schema defining the parameters accepted by the tool.", - "properties": { - "type": { - "type": "string", - "description": "The type of the parameters object (usually 'object')." - }, - "required": { - "type": "array", - "description": "List of required parameter names.", - "items": { - "type": "string" - } - }, - "properties": { - "type": "object", - "description": "Definitions of each parameter.", - "additionalProperties": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "The data type of the parameter." - }, - "description": { - "type": "string", - "description": "A description of the expected parameter." - } - }, - "required": [ - "type", - "description" - ] - } - } - }, - "required": [ - "type", - "properties" - ] - } - }, - "required": [ - "name", - "description", - "parameters" - ] - }, - { - "properties": { - "type": { - "type": "string", - "description": "Specifies the type of tool (e.g., 'function')." - }, - "function": { - "type": "object", - "description": "Details of the function tool.", - "properties": { - "name": { - "type": "string", - "description": "The name of the function." - }, - "description": { - "type": "string", - "description": "A brief description of what the function does." - }, - "parameters": { - "type": "object", - "description": "Schema defining the parameters accepted by the function.", - "properties": { - "type": { - "type": "string", - "description": "The type of the parameters object (usually 'object')." - }, - "required": { - "type": "array", - "description": "List of required parameter names.", - "items": { - "type": "string" - } - }, - "properties": { - "type": "object", - "description": "Definitions of each parameter.", - "additionalProperties": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "The data type of the parameter." - }, - "description": { - "type": "string", - "description": "A description of the expected parameter." - } - }, - "required": [ - "type", - "description" - ] - } - } - }, - "required": [ - "type", - "properties" - ] - } - }, - "required": [ - "name", - "description", - "parameters" - ] - } - }, - "required": [ - "type", - "function" - ] - } - ] - } - }, - "response_format": { - "title": "JSON Mode", - "type": "object", - "properties": { - "type": { - "type": "string", - "enum": [ - "json_object", - "json_schema" - ] - }, - "json_schema": {} - } - }, - "raw": { - "type": "boolean", - "default": false, - "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." - }, - "stream": { - "type": "boolean", - "default": false, - "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." - }, - "max_tokens": { - "type": "integer", - "default": 256, - "description": "The maximum number of tokens to generate in the response." - }, - "temperature": { - "type": "number", - "default": 0.6, - "minimum": 0, - "maximum": 5, - "description": "Controls the randomness of the output; higher values produce more random results." - }, - "top_p": { - "type": "number", - "minimum": 0.001, - "maximum": 1, - "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." - }, - "top_k": { - "type": "integer", - "minimum": 1, - "maximum": 50, - "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." - }, - "seed": { - "type": "integer", - "minimum": 1, - "maximum": 9999999999, - "description": "Random seed for reproducibility of the generation." - }, - "repetition_penalty": { - "type": "number", - "minimum": 0, - "maximum": 2, - "description": "Penalty for repeated tokens; higher values discourage repetition." - }, - "frequency_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Decreases the likelihood of the model repeating the same lines verbatim." - }, - "presence_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Increases the likelihood of the model introducing new topics." - } - }, - "required": [ - "messages" - ] - } - ] - }, - "output": { - "oneOf": [ - { - "type": "object", - "properties": { - "response": { - "type": "string", - "description": "The generated text response from the model" - }, - "usage": { - "type": "object", - "description": "Usage statistics for the inference request", - "properties": { - "prompt_tokens": { - "type": "number", - "description": "Total number of tokens in input", - "default": 0 - }, - "completion_tokens": { - "type": "number", - "description": "Total number of tokens in output", - "default": 0 - }, - "total_tokens": { - "type": "number", - "description": "Total number of input and output tokens", - "default": 0 - } - } - }, - "tool_calls": { - "type": "array", - "description": "An array of tool calls requests made during the response generation", - "items": { - "type": "object", - "properties": { - "arguments": { - "type": "object", - "description": "The arguments passed to be passed to the tool call request" - }, - "name": { - "type": "string", - "description": "The name of the tool to be called" - } - } - } - } - }, - "required": [ - "response" - ] - }, - { - "type": "string", - "format": "binary" - } - ] - } - } -} \ No newline at end of file diff --git a/src/content/workers-ai-models/starling-lm-7b-beta.json b/src/content/workers-ai-models/starling-lm-7b-beta.json deleted file mode 100644 index 46f7263402dc5a7..000000000000000 --- a/src/content/workers-ai-models/starling-lm-7b-beta.json +++ /dev/null @@ -1,478 +0,0 @@ -{ - "id": "e5ca943b-720f-4e66-aa8f-40e3d2770933", - "source": 2, - "name": "@hf/nexusflow/starling-lm-7b-beta", - "description": "We introduce Starling-LM-7B-beta, an open large language model (LLM) trained by Reinforcement Learning from AI Feedback (RLAIF). Starling-LM-7B-beta is trained from Openchat-3.5-0106 with our new reward model Nexusflow/Starling-RM-34B and policy optimization method Fine-Tuning Language Models from Human Preferences (PPO).", - "task": { - "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", - "name": "Text Generation", - "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." - }, - "created_at": "2024-04-01 23:49:31.797", - "tags": [], - "properties": [ - { - "property_id": "beta", - "value": "true" - }, - { - "property_id": "context_window", - "value": "4096" - }, - { - "property_id": "info", - "value": "https://huggingface.co/Nexusflow/Starling-LM-7B-beta" - }, - { - "property_id": "max_batch_prefill_tokens", - "value": "8192" - }, - { - "property_id": "max_input_length", - "value": "3072" - }, - { - "property_id": "max_total_tokens", - "value": "4096" - }, - { - "property_id": "planned_deprecation_date", - "value": "2025-10-01" - } - ], - "schema": { - "input": { - "type": "object", - "oneOf": [ - { - "title": "Prompt", - "properties": { - "prompt": { - "type": "string", - "minLength": 1, - "description": "The input text prompt for the model to generate a response." - }, - "lora": { - "type": "string", - "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." - }, - "response_format": { - "title": "JSON Mode", - "type": "object", - "properties": { - "type": { - "type": "string", - "enum": [ - "json_object", - "json_schema" - ] - }, - "json_schema": {} - } - }, - "raw": { - "type": "boolean", - "default": false, - "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." - }, - "stream": { - "type": "boolean", - "default": false, - "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." - }, - "max_tokens": { - "type": "integer", - "default": 256, - "description": "The maximum number of tokens to generate in the response." - }, - "temperature": { - "type": "number", - "default": 0.6, - "minimum": 0, - "maximum": 5, - "description": "Controls the randomness of the output; higher values produce more random results." - }, - "top_p": { - "type": "number", - "minimum": 0.001, - "maximum": 1, - "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." - }, - "top_k": { - "type": "integer", - "minimum": 1, - "maximum": 50, - "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." - }, - "seed": { - "type": "integer", - "minimum": 1, - "maximum": 9999999999, - "description": "Random seed for reproducibility of the generation." - }, - "repetition_penalty": { - "type": "number", - "minimum": 0, - "maximum": 2, - "description": "Penalty for repeated tokens; higher values discourage repetition." - }, - "frequency_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Decreases the likelihood of the model repeating the same lines verbatim." - }, - "presence_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Increases the likelihood of the model introducing new topics." - } - }, - "required": [ - "prompt" - ] - }, - { - "title": "Messages", - "properties": { - "messages": { - "type": "array", - "description": "An array of message objects representing the conversation history.", - "items": { - "type": "object", - "properties": { - "role": { - "type": "string", - "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." - }, - "content": { - "oneOf": [ - { - "type": "string", - "description": "The content of the message as a string." - }, - { - "type": "array", - "description": "Array of text content parts.", - "items": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "Type of the content (text)" - }, - "text": { - "type": "string", - "description": "Text content" - } - } - } - } - ] - } - }, - "required": [ - "role", - "content" - ] - } - }, - "functions": { - "type": "array", - "items": { - "type": "object", - "properties": { - "name": { - "type": "string" - }, - "code": { - "type": "string" - } - }, - "required": [ - "name", - "code" - ] - } - }, - "tools": { - "type": "array", - "description": "A list of tools available for the assistant to use.", - "items": { - "type": "object", - "oneOf": [ - { - "properties": { - "name": { - "type": "string", - "description": "The name of the tool. More descriptive the better." - }, - "description": { - "type": "string", - "description": "A brief description of what the tool does." - }, - "parameters": { - "type": "object", - "description": "Schema defining the parameters accepted by the tool.", - "properties": { - "type": { - "type": "string", - "description": "The type of the parameters object (usually 'object')." - }, - "required": { - "type": "array", - "description": "List of required parameter names.", - "items": { - "type": "string" - } - }, - "properties": { - "type": "object", - "description": "Definitions of each parameter.", - "additionalProperties": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "The data type of the parameter." - }, - "description": { - "type": "string", - "description": "A description of the expected parameter." - } - }, - "required": [ - "type", - "description" - ] - } - } - }, - "required": [ - "type", - "properties" - ] - } - }, - "required": [ - "name", - "description", - "parameters" - ] - }, - { - "properties": { - "type": { - "type": "string", - "description": "Specifies the type of tool (e.g., 'function')." - }, - "function": { - "type": "object", - "description": "Details of the function tool.", - "properties": { - "name": { - "type": "string", - "description": "The name of the function." - }, - "description": { - "type": "string", - "description": "A brief description of what the function does." - }, - "parameters": { - "type": "object", - "description": "Schema defining the parameters accepted by the function.", - "properties": { - "type": { - "type": "string", - "description": "The type of the parameters object (usually 'object')." - }, - "required": { - "type": "array", - "description": "List of required parameter names.", - "items": { - "type": "string" - } - }, - "properties": { - "type": "object", - "description": "Definitions of each parameter.", - "additionalProperties": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "The data type of the parameter." - }, - "description": { - "type": "string", - "description": "A description of the expected parameter." - } - }, - "required": [ - "type", - "description" - ] - } - } - }, - "required": [ - "type", - "properties" - ] - } - }, - "required": [ - "name", - "description", - "parameters" - ] - } - }, - "required": [ - "type", - "function" - ] - } - ] - } - }, - "response_format": { - "title": "JSON Mode", - "type": "object", - "properties": { - "type": { - "type": "string", - "enum": [ - "json_object", - "json_schema" - ] - }, - "json_schema": {} - } - }, - "raw": { - "type": "boolean", - "default": false, - "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." - }, - "stream": { - "type": "boolean", - "default": false, - "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." - }, - "max_tokens": { - "type": "integer", - "default": 256, - "description": "The maximum number of tokens to generate in the response." - }, - "temperature": { - "type": "number", - "default": 0.6, - "minimum": 0, - "maximum": 5, - "description": "Controls the randomness of the output; higher values produce more random results." - }, - "top_p": { - "type": "number", - "minimum": 0.001, - "maximum": 1, - "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." - }, - "top_k": { - "type": "integer", - "minimum": 1, - "maximum": 50, - "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." - }, - "seed": { - "type": "integer", - "minimum": 1, - "maximum": 9999999999, - "description": "Random seed for reproducibility of the generation." - }, - "repetition_penalty": { - "type": "number", - "minimum": 0, - "maximum": 2, - "description": "Penalty for repeated tokens; higher values discourage repetition." - }, - "frequency_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Decreases the likelihood of the model repeating the same lines verbatim." - }, - "presence_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Increases the likelihood of the model introducing new topics." - } - }, - "required": [ - "messages" - ] - } - ] - }, - "output": { - "oneOf": [ - { - "type": "object", - "properties": { - "response": { - "type": "string", - "description": "The generated text response from the model" - }, - "usage": { - "type": "object", - "description": "Usage statistics for the inference request", - "properties": { - "prompt_tokens": { - "type": "number", - "description": "Total number of tokens in input", - "default": 0 - }, - "completion_tokens": { - "type": "number", - "description": "Total number of tokens in output", - "default": 0 - }, - "total_tokens": { - "type": "number", - "description": "Total number of input and output tokens", - "default": 0 - } - } - }, - "tool_calls": { - "type": "array", - "description": "An array of tool calls requests made during the response generation", - "items": { - "type": "object", - "properties": { - "arguments": { - "type": "object", - "description": "The arguments passed to be passed to the tool call request" - }, - "name": { - "type": "string", - "description": "The name of the tool to be called" - } - } - } - } - }, - "required": [ - "response" - ] - }, - { - "type": "string", - "format": "binary" - } - ] - } - } -} \ No newline at end of file diff --git a/src/content/workers-ai-models/tinyllama-1.1b-chat-v1.0.json b/src/content/workers-ai-models/tinyllama-1.1b-chat-v1.0.json deleted file mode 100644 index 5cab744b8fafa2a..000000000000000 --- a/src/content/workers-ai-models/tinyllama-1.1b-chat-v1.0.json +++ /dev/null @@ -1,466 +0,0 @@ -{ - "id": "bf6ddd21-6477-4681-bbbe-24c3d5423e78", - "source": 1, - "name": "@cf/tinyllama/tinyllama-1.1b-chat-v1.0", - "description": "The TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens. This is the chat model finetuned on top of TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T.", - "task": { - "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", - "name": "Text Generation", - "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." - }, - "created_at": "2024-02-27 18:25:37.524", - "tags": [], - "properties": [ - { - "property_id": "beta", - "value": "true" - }, - { - "property_id": "context_window", - "value": "2048" - }, - { - "property_id": "info", - "value": "https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0" - }, - { - "property_id": "planned_deprecation_date", - "value": "2025-10-01" - } - ], - "schema": { - "input": { - "type": "object", - "oneOf": [ - { - "title": "Prompt", - "properties": { - "prompt": { - "type": "string", - "minLength": 1, - "description": "The input text prompt for the model to generate a response." - }, - "lora": { - "type": "string", - "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." - }, - "response_format": { - "title": "JSON Mode", - "type": "object", - "properties": { - "type": { - "type": "string", - "enum": [ - "json_object", - "json_schema" - ] - }, - "json_schema": {} - } - }, - "raw": { - "type": "boolean", - "default": false, - "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." - }, - "stream": { - "type": "boolean", - "default": false, - "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." - }, - "max_tokens": { - "type": "integer", - "default": 256, - "description": "The maximum number of tokens to generate in the response." - }, - "temperature": { - "type": "number", - "default": 0.6, - "minimum": 0, - "maximum": 5, - "description": "Controls the randomness of the output; higher values produce more random results." - }, - "top_p": { - "type": "number", - "minimum": 0.001, - "maximum": 1, - "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." - }, - "top_k": { - "type": "integer", - "minimum": 1, - "maximum": 50, - "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." - }, - "seed": { - "type": "integer", - "minimum": 1, - "maximum": 9999999999, - "description": "Random seed for reproducibility of the generation." - }, - "repetition_penalty": { - "type": "number", - "minimum": 0, - "maximum": 2, - "description": "Penalty for repeated tokens; higher values discourage repetition." - }, - "frequency_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Decreases the likelihood of the model repeating the same lines verbatim." - }, - "presence_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Increases the likelihood of the model introducing new topics." - } - }, - "required": [ - "prompt" - ] - }, - { - "title": "Messages", - "properties": { - "messages": { - "type": "array", - "description": "An array of message objects representing the conversation history.", - "items": { - "type": "object", - "properties": { - "role": { - "type": "string", - "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." - }, - "content": { - "oneOf": [ - { - "type": "string", - "description": "The content of the message as a string." - }, - { - "type": "array", - "description": "Array of text content parts.", - "items": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "Type of the content (text)" - }, - "text": { - "type": "string", - "description": "Text content" - } - } - } - } - ] - } - }, - "required": [ - "role", - "content" - ] - } - }, - "functions": { - "type": "array", - "items": { - "type": "object", - "properties": { - "name": { - "type": "string" - }, - "code": { - "type": "string" - } - }, - "required": [ - "name", - "code" - ] - } - }, - "tools": { - "type": "array", - "description": "A list of tools available for the assistant to use.", - "items": { - "type": "object", - "oneOf": [ - { - "properties": { - "name": { - "type": "string", - "description": "The name of the tool. More descriptive the better." - }, - "description": { - "type": "string", - "description": "A brief description of what the tool does." - }, - "parameters": { - "type": "object", - "description": "Schema defining the parameters accepted by the tool.", - "properties": { - "type": { - "type": "string", - "description": "The type of the parameters object (usually 'object')." - }, - "required": { - "type": "array", - "description": "List of required parameter names.", - "items": { - "type": "string" - } - }, - "properties": { - "type": "object", - "description": "Definitions of each parameter.", - "additionalProperties": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "The data type of the parameter." - }, - "description": { - "type": "string", - "description": "A description of the expected parameter." - } - }, - "required": [ - "type", - "description" - ] - } - } - }, - "required": [ - "type", - "properties" - ] - } - }, - "required": [ - "name", - "description", - "parameters" - ] - }, - { - "properties": { - "type": { - "type": "string", - "description": "Specifies the type of tool (e.g., 'function')." - }, - "function": { - "type": "object", - "description": "Details of the function tool.", - "properties": { - "name": { - "type": "string", - "description": "The name of the function." - }, - "description": { - "type": "string", - "description": "A brief description of what the function does." - }, - "parameters": { - "type": "object", - "description": "Schema defining the parameters accepted by the function.", - "properties": { - "type": { - "type": "string", - "description": "The type of the parameters object (usually 'object')." - }, - "required": { - "type": "array", - "description": "List of required parameter names.", - "items": { - "type": "string" - } - }, - "properties": { - "type": "object", - "description": "Definitions of each parameter.", - "additionalProperties": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "The data type of the parameter." - }, - "description": { - "type": "string", - "description": "A description of the expected parameter." - } - }, - "required": [ - "type", - "description" - ] - } - } - }, - "required": [ - "type", - "properties" - ] - } - }, - "required": [ - "name", - "description", - "parameters" - ] - } - }, - "required": [ - "type", - "function" - ] - } - ] - } - }, - "response_format": { - "title": "JSON Mode", - "type": "object", - "properties": { - "type": { - "type": "string", - "enum": [ - "json_object", - "json_schema" - ] - }, - "json_schema": {} - } - }, - "raw": { - "type": "boolean", - "default": false, - "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." - }, - "stream": { - "type": "boolean", - "default": false, - "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." - }, - "max_tokens": { - "type": "integer", - "default": 256, - "description": "The maximum number of tokens to generate in the response." - }, - "temperature": { - "type": "number", - "default": 0.6, - "minimum": 0, - "maximum": 5, - "description": "Controls the randomness of the output; higher values produce more random results." - }, - "top_p": { - "type": "number", - "minimum": 0.001, - "maximum": 1, - "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." - }, - "top_k": { - "type": "integer", - "minimum": 1, - "maximum": 50, - "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." - }, - "seed": { - "type": "integer", - "minimum": 1, - "maximum": 9999999999, - "description": "Random seed for reproducibility of the generation." - }, - "repetition_penalty": { - "type": "number", - "minimum": 0, - "maximum": 2, - "description": "Penalty for repeated tokens; higher values discourage repetition." - }, - "frequency_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Decreases the likelihood of the model repeating the same lines verbatim." - }, - "presence_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Increases the likelihood of the model introducing new topics." - } - }, - "required": [ - "messages" - ] - } - ] - }, - "output": { - "oneOf": [ - { - "type": "object", - "properties": { - "response": { - "type": "string", - "description": "The generated text response from the model" - }, - "usage": { - "type": "object", - "description": "Usage statistics for the inference request", - "properties": { - "prompt_tokens": { - "type": "number", - "description": "Total number of tokens in input", - "default": 0 - }, - "completion_tokens": { - "type": "number", - "description": "Total number of tokens in output", - "default": 0 - }, - "total_tokens": { - "type": "number", - "description": "Total number of input and output tokens", - "default": 0 - } - } - }, - "tool_calls": { - "type": "array", - "description": "An array of tool calls requests made during the response generation", - "items": { - "type": "object", - "properties": { - "arguments": { - "type": "object", - "description": "The arguments passed to be passed to the tool call request" - }, - "name": { - "type": "string", - "description": "The name of the tool to be called" - } - } - } - } - }, - "required": [ - "response" - ] - }, - { - "type": "string", - "format": "binary" - } - ] - } - } -} \ No newline at end of file diff --git a/src/content/workers-ai-models/una-cybertron-7b-v2-bf16.json b/src/content/workers-ai-models/una-cybertron-7b-v2-bf16.json deleted file mode 100644 index 79ee822bdeec49d..000000000000000 --- a/src/content/workers-ai-models/una-cybertron-7b-v2-bf16.json +++ /dev/null @@ -1,462 +0,0 @@ -{ - "id": "b7fe7ad2-aeaf-47d2-8bfa-7a5ae22a2ab4", - "source": 1, - "name": "@cf/fblgit/una-cybertron-7b-v2-bf16", - "description": "Cybertron 7B v2 is a 7B MistralAI based model, best on it's series. It was trained with SFT, DPO and UNA (Unified Neural Alignment) on multiple datasets.", - "task": { - "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", - "name": "Text Generation", - "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." - }, - "created_at": "2024-04-24 14:37:19.494", - "tags": [], - "properties": [ - { - "property_id": "beta", - "value": "true" - }, - { - "property_id": "context_window", - "value": "15000" - }, - { - "property_id": "planned_deprecation_date", - "value": "2025-10-01" - } - ], - "schema": { - "input": { - "type": "object", - "oneOf": [ - { - "title": "Prompt", - "properties": { - "prompt": { - "type": "string", - "minLength": 1, - "description": "The input text prompt for the model to generate a response." - }, - "lora": { - "type": "string", - "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." - }, - "response_format": { - "title": "JSON Mode", - "type": "object", - "properties": { - "type": { - "type": "string", - "enum": [ - "json_object", - "json_schema" - ] - }, - "json_schema": {} - } - }, - "raw": { - "type": "boolean", - "default": false, - "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." - }, - "stream": { - "type": "boolean", - "default": false, - "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." - }, - "max_tokens": { - "type": "integer", - "default": 256, - "description": "The maximum number of tokens to generate in the response." - }, - "temperature": { - "type": "number", - "default": 0.6, - "minimum": 0, - "maximum": 5, - "description": "Controls the randomness of the output; higher values produce more random results." - }, - "top_p": { - "type": "number", - "minimum": 0.001, - "maximum": 1, - "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." - }, - "top_k": { - "type": "integer", - "minimum": 1, - "maximum": 50, - "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." - }, - "seed": { - "type": "integer", - "minimum": 1, - "maximum": 9999999999, - "description": "Random seed for reproducibility of the generation." - }, - "repetition_penalty": { - "type": "number", - "minimum": 0, - "maximum": 2, - "description": "Penalty for repeated tokens; higher values discourage repetition." - }, - "frequency_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Decreases the likelihood of the model repeating the same lines verbatim." - }, - "presence_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Increases the likelihood of the model introducing new topics." - } - }, - "required": [ - "prompt" - ] - }, - { - "title": "Messages", - "properties": { - "messages": { - "type": "array", - "description": "An array of message objects representing the conversation history.", - "items": { - "type": "object", - "properties": { - "role": { - "type": "string", - "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." - }, - "content": { - "oneOf": [ - { - "type": "string", - "description": "The content of the message as a string." - }, - { - "type": "array", - "description": "Array of text content parts.", - "items": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "Type of the content (text)" - }, - "text": { - "type": "string", - "description": "Text content" - } - } - } - } - ] - } - }, - "required": [ - "role", - "content" - ] - } - }, - "functions": { - "type": "array", - "items": { - "type": "object", - "properties": { - "name": { - "type": "string" - }, - "code": { - "type": "string" - } - }, - "required": [ - "name", - "code" - ] - } - }, - "tools": { - "type": "array", - "description": "A list of tools available for the assistant to use.", - "items": { - "type": "object", - "oneOf": [ - { - "properties": { - "name": { - "type": "string", - "description": "The name of the tool. More descriptive the better." - }, - "description": { - "type": "string", - "description": "A brief description of what the tool does." - }, - "parameters": { - "type": "object", - "description": "Schema defining the parameters accepted by the tool.", - "properties": { - "type": { - "type": "string", - "description": "The type of the parameters object (usually 'object')." - }, - "required": { - "type": "array", - "description": "List of required parameter names.", - "items": { - "type": "string" - } - }, - "properties": { - "type": "object", - "description": "Definitions of each parameter.", - "additionalProperties": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "The data type of the parameter." - }, - "description": { - "type": "string", - "description": "A description of the expected parameter." - } - }, - "required": [ - "type", - "description" - ] - } - } - }, - "required": [ - "type", - "properties" - ] - } - }, - "required": [ - "name", - "description", - "parameters" - ] - }, - { - "properties": { - "type": { - "type": "string", - "description": "Specifies the type of tool (e.g., 'function')." - }, - "function": { - "type": "object", - "description": "Details of the function tool.", - "properties": { - "name": { - "type": "string", - "description": "The name of the function." - }, - "description": { - "type": "string", - "description": "A brief description of what the function does." - }, - "parameters": { - "type": "object", - "description": "Schema defining the parameters accepted by the function.", - "properties": { - "type": { - "type": "string", - "description": "The type of the parameters object (usually 'object')." - }, - "required": { - "type": "array", - "description": "List of required parameter names.", - "items": { - "type": "string" - } - }, - "properties": { - "type": "object", - "description": "Definitions of each parameter.", - "additionalProperties": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "The data type of the parameter." - }, - "description": { - "type": "string", - "description": "A description of the expected parameter." - } - }, - "required": [ - "type", - "description" - ] - } - } - }, - "required": [ - "type", - "properties" - ] - } - }, - "required": [ - "name", - "description", - "parameters" - ] - } - }, - "required": [ - "type", - "function" - ] - } - ] - } - }, - "response_format": { - "title": "JSON Mode", - "type": "object", - "properties": { - "type": { - "type": "string", - "enum": [ - "json_object", - "json_schema" - ] - }, - "json_schema": {} - } - }, - "raw": { - "type": "boolean", - "default": false, - "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." - }, - "stream": { - "type": "boolean", - "default": false, - "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." - }, - "max_tokens": { - "type": "integer", - "default": 256, - "description": "The maximum number of tokens to generate in the response." - }, - "temperature": { - "type": "number", - "default": 0.6, - "minimum": 0, - "maximum": 5, - "description": "Controls the randomness of the output; higher values produce more random results." - }, - "top_p": { - "type": "number", - "minimum": 0.001, - "maximum": 1, - "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." - }, - "top_k": { - "type": "integer", - "minimum": 1, - "maximum": 50, - "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." - }, - "seed": { - "type": "integer", - "minimum": 1, - "maximum": 9999999999, - "description": "Random seed for reproducibility of the generation." - }, - "repetition_penalty": { - "type": "number", - "minimum": 0, - "maximum": 2, - "description": "Penalty for repeated tokens; higher values discourage repetition." - }, - "frequency_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Decreases the likelihood of the model repeating the same lines verbatim." - }, - "presence_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Increases the likelihood of the model introducing new topics." - } - }, - "required": [ - "messages" - ] - } - ] - }, - "output": { - "oneOf": [ - { - "type": "object", - "properties": { - "response": { - "type": "string", - "description": "The generated text response from the model" - }, - "usage": { - "type": "object", - "description": "Usage statistics for the inference request", - "properties": { - "prompt_tokens": { - "type": "number", - "description": "Total number of tokens in input", - "default": 0 - }, - "completion_tokens": { - "type": "number", - "description": "Total number of tokens in output", - "default": 0 - }, - "total_tokens": { - "type": "number", - "description": "Total number of input and output tokens", - "default": 0 - } - } - }, - "tool_calls": { - "type": "array", - "description": "An array of tool calls requests made during the response generation", - "items": { - "type": "object", - "properties": { - "arguments": { - "type": "object", - "description": "The arguments passed to be passed to the tool call request" - }, - "name": { - "type": "string", - "description": "The name of the tool to be called" - } - } - } - } - }, - "required": [ - "response" - ] - }, - { - "type": "string", - "format": "binary" - } - ] - } - } -} \ No newline at end of file diff --git a/src/content/workers-ai-models/zephyr-7b-beta-awq.json b/src/content/workers-ai-models/zephyr-7b-beta-awq.json deleted file mode 100644 index 4f0e97d65804ce2..000000000000000 --- a/src/content/workers-ai-models/zephyr-7b-beta-awq.json +++ /dev/null @@ -1,466 +0,0 @@ -{ - "id": "3976bab8-3810-4ad8-8580-ab1e22de7823", - "source": 2, - "name": "@hf/thebloke/zephyr-7b-beta-awq", - "description": "Zephyr 7B Beta AWQ is an efficient, accurate and blazing-fast low-bit weight quantized Zephyr model variant.", - "task": { - "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", - "name": "Text Generation", - "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." - }, - "created_at": "2023-11-24 00:27:15.869", - "tags": [], - "properties": [ - { - "property_id": "beta", - "value": "true" - }, - { - "property_id": "context_window", - "value": "4096" - }, - { - "property_id": "info", - "value": "https://huggingface.co/TheBloke/zephyr-7B-beta-AWQ" - }, - { - "property_id": "planned_deprecation_date", - "value": "2025-10-01" - } - ], - "schema": { - "input": { - "type": "object", - "oneOf": [ - { - "title": "Prompt", - "properties": { - "prompt": { - "type": "string", - "minLength": 1, - "description": "The input text prompt for the model to generate a response." - }, - "lora": { - "type": "string", - "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." - }, - "response_format": { - "title": "JSON Mode", - "type": "object", - "properties": { - "type": { - "type": "string", - "enum": [ - "json_object", - "json_schema" - ] - }, - "json_schema": {} - } - }, - "raw": { - "type": "boolean", - "default": false, - "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." - }, - "stream": { - "type": "boolean", - "default": false, - "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." - }, - "max_tokens": { - "type": "integer", - "default": 256, - "description": "The maximum number of tokens to generate in the response." - }, - "temperature": { - "type": "number", - "default": 0.6, - "minimum": 0, - "maximum": 5, - "description": "Controls the randomness of the output; higher values produce more random results." - }, - "top_p": { - "type": "number", - "minimum": 0.001, - "maximum": 1, - "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." - }, - "top_k": { - "type": "integer", - "minimum": 1, - "maximum": 50, - "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." - }, - "seed": { - "type": "integer", - "minimum": 1, - "maximum": 9999999999, - "description": "Random seed for reproducibility of the generation." - }, - "repetition_penalty": { - "type": "number", - "minimum": 0, - "maximum": 2, - "description": "Penalty for repeated tokens; higher values discourage repetition." - }, - "frequency_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Decreases the likelihood of the model repeating the same lines verbatim." - }, - "presence_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Increases the likelihood of the model introducing new topics." - } - }, - "required": [ - "prompt" - ] - }, - { - "title": "Messages", - "properties": { - "messages": { - "type": "array", - "description": "An array of message objects representing the conversation history.", - "items": { - "type": "object", - "properties": { - "role": { - "type": "string", - "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." - }, - "content": { - "oneOf": [ - { - "type": "string", - "description": "The content of the message as a string." - }, - { - "type": "array", - "description": "Array of text content parts.", - "items": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "Type of the content (text)" - }, - "text": { - "type": "string", - "description": "Text content" - } - } - } - } - ] - } - }, - "required": [ - "role", - "content" - ] - } - }, - "functions": { - "type": "array", - "items": { - "type": "object", - "properties": { - "name": { - "type": "string" - }, - "code": { - "type": "string" - } - }, - "required": [ - "name", - "code" - ] - } - }, - "tools": { - "type": "array", - "description": "A list of tools available for the assistant to use.", - "items": { - "type": "object", - "oneOf": [ - { - "properties": { - "name": { - "type": "string", - "description": "The name of the tool. More descriptive the better." - }, - "description": { - "type": "string", - "description": "A brief description of what the tool does." - }, - "parameters": { - "type": "object", - "description": "Schema defining the parameters accepted by the tool.", - "properties": { - "type": { - "type": "string", - "description": "The type of the parameters object (usually 'object')." - }, - "required": { - "type": "array", - "description": "List of required parameter names.", - "items": { - "type": "string" - } - }, - "properties": { - "type": "object", - "description": "Definitions of each parameter.", - "additionalProperties": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "The data type of the parameter." - }, - "description": { - "type": "string", - "description": "A description of the expected parameter." - } - }, - "required": [ - "type", - "description" - ] - } - } - }, - "required": [ - "type", - "properties" - ] - } - }, - "required": [ - "name", - "description", - "parameters" - ] - }, - { - "properties": { - "type": { - "type": "string", - "description": "Specifies the type of tool (e.g., 'function')." - }, - "function": { - "type": "object", - "description": "Details of the function tool.", - "properties": { - "name": { - "type": "string", - "description": "The name of the function." - }, - "description": { - "type": "string", - "description": "A brief description of what the function does." - }, - "parameters": { - "type": "object", - "description": "Schema defining the parameters accepted by the function.", - "properties": { - "type": { - "type": "string", - "description": "The type of the parameters object (usually 'object')." - }, - "required": { - "type": "array", - "description": "List of required parameter names.", - "items": { - "type": "string" - } - }, - "properties": { - "type": "object", - "description": "Definitions of each parameter.", - "additionalProperties": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "The data type of the parameter." - }, - "description": { - "type": "string", - "description": "A description of the expected parameter." - } - }, - "required": [ - "type", - "description" - ] - } - } - }, - "required": [ - "type", - "properties" - ] - } - }, - "required": [ - "name", - "description", - "parameters" - ] - } - }, - "required": [ - "type", - "function" - ] - } - ] - } - }, - "response_format": { - "title": "JSON Mode", - "type": "object", - "properties": { - "type": { - "type": "string", - "enum": [ - "json_object", - "json_schema" - ] - }, - "json_schema": {} - } - }, - "raw": { - "type": "boolean", - "default": false, - "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." - }, - "stream": { - "type": "boolean", - "default": false, - "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." - }, - "max_tokens": { - "type": "integer", - "default": 256, - "description": "The maximum number of tokens to generate in the response." - }, - "temperature": { - "type": "number", - "default": 0.6, - "minimum": 0, - "maximum": 5, - "description": "Controls the randomness of the output; higher values produce more random results." - }, - "top_p": { - "type": "number", - "minimum": 0.001, - "maximum": 1, - "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." - }, - "top_k": { - "type": "integer", - "minimum": 1, - "maximum": 50, - "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." - }, - "seed": { - "type": "integer", - "minimum": 1, - "maximum": 9999999999, - "description": "Random seed for reproducibility of the generation." - }, - "repetition_penalty": { - "type": "number", - "minimum": 0, - "maximum": 2, - "description": "Penalty for repeated tokens; higher values discourage repetition." - }, - "frequency_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Decreases the likelihood of the model repeating the same lines verbatim." - }, - "presence_penalty": { - "type": "number", - "minimum": -2, - "maximum": 2, - "description": "Increases the likelihood of the model introducing new topics." - } - }, - "required": [ - "messages" - ] - } - ] - }, - "output": { - "oneOf": [ - { - "type": "object", - "properties": { - "response": { - "type": "string", - "description": "The generated text response from the model" - }, - "usage": { - "type": "object", - "description": "Usage statistics for the inference request", - "properties": { - "prompt_tokens": { - "type": "number", - "description": "Total number of tokens in input", - "default": 0 - }, - "completion_tokens": { - "type": "number", - "description": "Total number of tokens in output", - "default": 0 - }, - "total_tokens": { - "type": "number", - "description": "Total number of input and output tokens", - "default": 0 - } - } - }, - "tool_calls": { - "type": "array", - "description": "An array of tool calls requests made during the response generation", - "items": { - "type": "object", - "properties": { - "arguments": { - "type": "object", - "description": "The arguments passed to be passed to the tool call request" - }, - "name": { - "type": "string", - "description": "The name of the tool to be called" - } - } - } - } - }, - "required": [ - "response" - ] - }, - { - "type": "string", - "format": "binary" - } - ] - } - } -} \ No newline at end of file