add-model-descriptions
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseAdd Model Descriptions
添加模型描述
Add descriptions for new models available in the HuggingFace router to chat-ui's prod.yaml and dev.yaml.
为HuggingFace Router中可用的新模型,在chat-ui的prod.yaml和dev.yaml文件中添加描述。
Workflow
工作流程
-
Fetch models from router
WebFetch https://router.huggingface.co/v1/modelsExtract all model IDs from the response. -
Read current configuration
- Read
chart/env/prod.yaml - Extract model IDs from the JSON array in
MODELSenvVars
- Read
-
Identify missing models Compare router models with prod.yaml. Missing = in router but not in prod.yaml.
-
Research each missing model For each missing model, search the web for its specifications:
- Model architecture (dense, MoE, parameters)
- Key capabilities (coding, reasoning, vision, multilingual, etc.)
- Target use cases
-
Write descriptions Match existing style:
- 8-12 words
- Sentence fragments (no period needed)
- No articles ("a", "the") unless necessary
- Focus on: architecture, specialization, key capability
Examples:"Flagship GLM MoE for coding, reasoning, and agentic tool use.""MoE agent model with multilingual coding and fast outputs.""Vision-language Qwen for documents, GUI agents, and visual reasoning.""Mobile agent for multilingual Android device automation."
-
Update both files Add new models at the TOP of the MODELS array in:
chart/env/prod.yamlchart/env/dev.yaml
Format:json{ "id": "org/model-name", "description": "Description here." } -
Commit changes
git add chart/env/prod.yaml chart/env/dev.yaml git commit -m "feat: add descriptions for N new models from router"
-
从Router获取模型
WebFetch https://router.huggingface.co/v1/models从响应中提取所有模型ID。 -
读取当前配置
- 读取文件
chart/env/prod.yaml - 从中的
envVarsJSON数组提取模型IDMODELS
- 读取
-
识别缺失的模型 对比Router中的模型与prod.yaml中的模型。缺失的模型指存在于Router但未在prod.yaml中的模型。
-
调研每个缺失的模型 针对每个缺失的模型,通过网络搜索其规格信息:
- 模型架构(密集型、MoE、参数规模)
- 核心能力(编码、推理、视觉、多语言等)
- 目标使用场景
-
撰写描述 匹配现有格式要求:
- 8-12个单词
- 句子片段(无需句号)
- 除非必要,否则不使用冠词("a"、"the")
- 重点涵盖:架构、专长领域、核心能力
示例:"Flagship GLM MoE for coding, reasoning, and agentic tool use.""MoE agent model with multilingual coding and fast outputs.""Vision-language Qwen for documents, GUI agents, and visual reasoning.""Mobile agent for multilingual Android device automation."
-
更新两个配置文件 在以下文件的数组顶部添加新模型:
MODELSchart/env/prod.yamlchart/env/dev.yaml
格式:json{ "id": "org/model-name", "description": "Description here." } -
提交更改
git add chart/env/prod.yaml chart/env/dev.yaml git commit -m "feat: add descriptions for N new models from router"
Notes
注意事项
- FP8 variants: describe as "FP8 [base model] for efficient inference with [key capability]"
- Vision models: mention "vision-language" and key visual tasks
- Agent models: mention "agent" and automation capabilities
- Regional models: mention language focus (e.g., "European multilingual", "Southeast Asian")
- FP8变体:描述格式为“FP8 [基础模型],具备[核心能力]的高效推理”
- 视觉模型:需提及“视觉-语言”及核心视觉任务
- Agent模型:需提及“agent”及自动化能力
- 区域模型:需提及语言侧重点(例如:“欧洲多语言”、“东南亚语言”)