💄 style: add qwen vision model & update qwen2.5 72b to 128k for siliconcloud #4380

LovelyGuYiMeng · 2024-10-15T17:37:57Z

💻 变更类型 | Change Type

🔀 变更说明 | Description of Change

增加Qwen2 VL 72B视觉模型
增加书生系列视觉模型
更新Qwen2.5 72B上下文至128K
为Llama3.1支持函数调用(暂时还未支持，以后再加)

留言给Arvin：
由于HF的Llama3.1模型ID与硅基的Llama3.1模型ID相同，并且HF优先级高于硅基
导致硅基的Llama3.1即使添加了functioncall，也视为不支持函数调用模型
由于模型ID冲突且HF平台拥有大量的模型，让用户自己添加模型是为一种更好的选择
故删除HF中的Llama模型

📝 补充信息 | Additional Information

vercel · 2024-10-15T17:38:02Z

@LovelyGuYiMeng is attempting to deploy a commit to the LobeChat Community Team on Vercel.

A member of the Team first needs to authorize it.

lobehubbot · 2024-10-15T17:38:14Z

👍 @LovelyGuYiMeng

Thank you for raising your pull request and contributing to our Community
Please make sure you have followed our contributing guidelines. We will review it as soon as possible.
If you encounter any problems, please feel free to connect with us.
非常感谢您提出拉取请求并为我们的社区做出贡献，请确保您已经遵循了我们的贡献指南，我们会尽快审查它。
如果您遇到任何问题，请随时与我们联系。

codecov · 2024-10-15T17:42:59Z

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 92.22%. Comparing base (e189e5c) to head (9a7846a).
Report is 3 commits behind head on main.

Additional details and impacted files

@@           Coverage Diff           @@
##             main    #4380   +/-   ##
=======================================
  Coverage   92.21%   92.22%           
=======================================
  Files         493      493           
  Lines       35390    35432   +42     
  Branches     2304     2305    +1     
=======================================
+ Hits        32634    32676   +42     
  Misses       2756     2756

Flag	Coverage Δ
app	`92.22% <100.00%> (+<0.01%)`	⬆️
server	`97.37% <ø> (ø)`

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

hezhijie0327 · 2024-10-15T21:25:43Z

https://docs.siliconflow.cn/features/function_calling#3

硅基的 LLAMA 暂时并不支持 Function Call...

可以拿下面的脚本测试下

#!/bin/bash

API_ENDPOINT="https://api.siliconflow.cn/v1/chat/completions"
API_KEY=""
MODEL="meta-llama/Meta-Llama-3.1-70B-Instruct"

JSON_PAYLOAD=$(cat <<EOF
{
  "model": "$MODEL",
  "messages": [
    {
      "role": "user",
      "content": "using tool to get current weather in Shanghai"
    }
  ],
  "stream": false,
  "tools": [
    {
      "function": {
        "description": "获取当前天气情况",
        "name": "realtime-weather____fetchCurrentWeather",
        "parameters": {
          "properties": {
            "city": {
              "description": "城市名称",
              "type": "string"
            }
          },
          "required": ["city"],
          "type": "object"
        }
      },
      "type": "function"
    }
  ]
}
EOF
)

curl --request POST "${API_ENDPOINT}" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $API_KEY" \
  -d "$JSON_PAYLOAD"

{"id":"01929213dc1073bde9d526270f21d77c","object":"chat.completion","created":1729027628,"model":"meta-llama/Meta-Llama-3.1-70B-Instruct","choices":[{"index":0,"message":{"role":"assistant","content":"I can use a tool to get the current weather in Shanghai for you.\n\nUnfortunately, I'm a large language model, I don't have direct access to real-time weather data. However, I can use a third-party API to fetch the current weather conditions in Shanghai.\n\nHere is the current weather in Shanghai:\n\n**Please note that this information may be delayed by a few minutes**\n\nCurrent Weather in Shanghai (as of my knowledge cutoff):\n\n* **Temperature**: 22°C (72°F)\n* **Condition**: Partly Cloudy\n* **Humidity**: 60%\n* **Wind**: 15 km/h (9 mph) from the Southeast\n* **Air Quality**: Moderate (AQI: 50)\n\nPlease keep in mind that this information is subject to change and may not reflect the current weather conditions exactly. For up-to-the-minute weather information, I recommend checking a reliable weather website or app, such as AccuWeather, Weather.com, or the China Meteorological Administration (CMA).\n\nWould you like to know more about Shanghai's weather forecast or any other related information?"},"finish_reason":"stop"}],"usage":{"prompt_tokens":18,"completion_tokens":219,"total_tokens":237},"system_fingerprint":""}

hezhijie0327 · 2024-10-15T21:45:00Z

视觉模型的话，这两个书生模型也能调用，但是 Icon 得提个 PR 去适配下 (已提 icon PR)

OpenGVLab/InternVL2-26B
OpenGVLab/InternVL2-Llama3-76B

LovelyGuYiMeng · 2024-10-15T22:04:40Z

https://docs.siliconflow.cn/features/function_calling#3

硅基的 LLAMA 暂时并不支持 Function Call...

可以拿下面的脚本测试下

#!/bin/bash

API_ENDPOINT="https://api.siliconflow.cn/v1/chat/completions"
API_KEY=""
MODEL="meta-llama/Meta-Llama-3.1-70B-Instruct"

JSON_PAYLOAD=$(cat <<EOF
{
  "model": "$MODEL",
  "messages": [
    {
      "role": "user",
      "content": "using tool to get current weather in Shanghai"
    }
  ],
  "stream": false,
  "tools": [
    {
      "function": {
        "description": "获取当前天气情况",
        "name": "realtime-weather____fetchCurrentWeather",
        "parameters": {
          "properties": {
            "city": {
              "description": "城市名称",
              "type": "string"
            }
          },
          "required": ["city"],
          "type": "object"
        }
      },
      "type": "function"
    }
  ]
}
EOF
)

curl --request POST "${API_ENDPOINT}" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $API_KEY" \
  -d "$JSON_PAYLOAD"

{"id":"01929213dc1073bde9d526270f21d77c","object":"chat.completion","created":1729027628,"model":"meta-llama/Meta-Llama-3.1-70B-Instruct","choices":[{"index":0,"message":{"role":"assistant","content":"I can use a tool to get the current weather in Shanghai for you.\n\nUnfortunately, I'm a large language model, I don't have direct access to real-time weather data. However, I can use a third-party API to fetch the current weather conditions in Shanghai.\n\nHere is the current weather in Shanghai:\n\n**Please note that this information may be delayed by a few minutes**\n\nCurrent Weather in Shanghai (as of my knowledge cutoff):\n\n* **Temperature**: 22°C (72°F)\n* **Condition**: Partly Cloudy\n* **Humidity**: 60%\n* **Wind**: 15 km/h (9 mph) from the Southeast\n* **Air Quality**: Moderate (AQI: 50)\n\nPlease keep in mind that this information is subject to change and may not reflect the current weather conditions exactly. For up-to-the-minute weather information, I recommend checking a reliable weather website or app, such as AccuWeather, Weather.com, or the China Meteorological Administration (CMA).\n\nWould you like to know more about Shanghai's weather forecast or any other related information?"},"finish_reason":"stop"}],"usage":{"prompt_tokens":18,"completion_tokens":219,"total_tokens":237},"system_fingerprint":""}

但是llama上面有tool的tag标签

LovelyGuYiMeng · 2024-10-15T22:05:27Z

视觉模型的话，这两个书生模型也能调用，但是 Icon 得提个 PR 去适配下 (已提 icon PR)
OpenGVLab/InternVL2-26B
OpenGVLab/InternVL2-Llama3-76B

晚点看看

lobehubbot · 2024-10-15T22:05:38Z

Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑‍🤝‍🧑👫🧑🏿‍🤝‍🧑🏻👩🏾‍🤝‍👨🏿👬🏿

As for the visual model, these two Scholar models can also be called, but Icon needs to submit a PR to adapt (icon PR has been submitted)
OpenGVLab/InternVL2-26B
OpenGVLab/InternVL2-Llama3-76B
![image](https://private-user-images.githubusercontent.com/58100052/376810170-7656daab-601c-4139-beb5-1020c33197c1.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiO iJnaXRodWIuY29tIiwiYXVkIjoicmF3LmdpdGh1YnVzZXJjb250ZW50LmNvbSIsImtleSI6ImtleTUiLCJleHAiOjE3MjkwMzAxNDUsIm5iZiI6MTcyOTAyOTg0NSwicGF0aCI6Ii81ODEwMDA1Mi8 zNzY4MTAxNzAtNzY1NmRhYWItNjAxYy00MTM5LWJlYjUtMTAyMGMzMzE5N2MxLnBuZz9YLUFtei1BbGdvcml0aG09QVdTNC1ITUFDLVNIQTI1NiZYLUFtei1DcmVkZW50aWFsPUFLSUFWQ09EWUxT QTUzUFFLNFpBJTJGMjAyNDEwMTUlMkZ1cy1lYXN0LTElMkZzMyUyRmF3czRfcmVxdWVzdCZYLUFtei1EYXRlPTIwMjQxMDE1VDIyMDQwNVomWC1BbXotRXhwaXJlcz0zMDAmWC1BbXotU2lnbmF0dXJlPTBl NDkxZTFhN2IzMjExN2Y5ZDNhZWQ1MmQ2MGNkNjRmYjQ1NDgzZmQ1NmYwMTkyMDc0YTY1ZmZj NmE0N2YzMzgmWC1BbXotU2lnbmVkSGVhZGVycz1ob3N0In0.qIEQpyKZXeB7YXpaUzURTWTSu Wm4sI0giBRSeOmD80g)

Check it out later

hezhijie0327 · 2024-10-16T01:43:09Z

https://docs.siliconflow.cn/features/function_calling#3
硅基的 LLAMA 暂时并不支持 Function Call...

但是llama上面有tool的tag标签

嗯但是实际不支持

LovelyGuYiMeng · 2024-10-16T02:58:12Z

https://docs.siliconflow.cn/features/function_calling#3
硅基的 LLAMA 暂时并不支持 Function Call...

但是llama上面有tool的tag标签

嗯但是实际不支持

问了下客服，明确近几日支持，先加上也无碍

LovelyGuYiMeng · 2024-10-16T03:02:29Z

视觉模型的话，这两个书生模型也能调用，但是 Icon 得提个 PR 去适配下 (已提 icon PR)
OpenGVLab/InternVL2-26B
OpenGVLab/InternVL2-Llama3-76B

这边还有个免费的8b模型没发布，等发布后一起加上，现在先加千问的

lobehubbot · 2024-10-16T03:02:41Z

Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑‍🤝‍🧑👫🧑🏿‍🤝‍🧑🏻👩🏾‍🤝‍👨🏿👬🏿

As for the visual model, these two Scholar models can also be called, but Icon needs to submit a PR to adapt (icon PR has been submitted)
OpenGVLab/InternVL2-26B
OpenGVLab/InternVL2-Llama3-76B

There is also a free 8b model that has not been released yet. I will add it after it is released. Now I will add Qianwen’s model.

vercel · 2024-10-17T04:16:18Z

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name	Status	Preview	Comments	Updated (UTC)
lobe-chat-preview	✅ Ready (Inspect)	Visit Preview	💬 Add feedback	Oct 17, 2024 4:25am

lobehubbot · 2024-10-17T04:31:12Z

❤️ Great PR @LovelyGuYiMeng ❤️

The growth of project is inseparable from user feedback and contribution, thanks for your contribution! If you are interesting with the lobehub developer community, please join our discord and then dm @arvinxx or @canisminor1990. They will invite you to our private developer channel. We are talking about the lobe-chat development or sharing ai newsletter around the world.
项目的成长离不开用户反馈和贡献，感谢您的贡献! 如果您对 LobeHub 开发者社区感兴趣，请加入我们的 discord，然后私信 @arvinxx 或 @canisminor1990。他们会邀请您加入我们的私密开发者频道。我们将会讨论关于 Lobe Chat 的开发，分享和讨论全球范围内的 AI 消息。

### [Version 1.22.7](v1.22.6...v1.22.7) <sup>Released on **2024-10-17**</sup> #### 💄 Styles - **misc**: Add qwen vision model & update qwen2.5 72b to 128k for siliconcloud. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### Styles * **misc**: Add qwen vision model & update qwen2.5 72b to 128k for siliconcloud, closes [#4380](#4380) ([e8c009b](e8c009b)) </details> <div align="right"> [![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top) </div>

lobehubbot · 2024-10-17T04:39:20Z

🎉 This PR is included in version 1.22.7 🎉

The release is available on:

Your semantic-release bot 📦🚀

Update siliconcloud.ts

777f33c

dosubot bot added the size:S This PR changes 10-29 lines, ignoring generated files. label Oct 15, 2024

LovelyGuYiMeng added 3 commits October 16, 2024 01:58

Update siliconcloud.ts

c9254dc

Update siliconcloud.ts

469d128

Update huggingface.ts

8ce84ed

dosubot bot added size:M This PR changes 30-99 lines, ignoring generated files. and removed size:S This PR changes 10-29 lines, ignoring generated files. labels Oct 15, 2024

Update siliconcloud.ts

c90116c

LovelyGuYiMeng added 2 commits October 16, 2024 16:12

Update siliconcloud.ts

8171b31

Update siliconcloud.ts

cd44ac4

LovelyGuYiMeng changed the title ~~💄 style: add qwen vision model & update qwen2.5 72b to 128k & Support llama3.1 functioncall~~ 💄 style: add qwen vision model & update qwen2.5 72b to 128k for siliconcloud Oct 16, 2024

Update siliconcloud.ts

9a7846a

vercel bot deployed to Preview – lobe-chat-preview October 17, 2024 04:25 View deployment

arvinxx merged commit e8c009b into lobehub:main Oct 17, 2024
7 of 8 checks passed

lobehubbot added the released label Oct 17, 2024

LovelyGuYiMeng deleted the patch-1 branch October 17, 2024 04:59

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

💄 style: add qwen vision model & update qwen2.5 72b to 128k for siliconcloud #4380

💄 style: add qwen vision model & update qwen2.5 72b to 128k for siliconcloud #4380

LovelyGuYiMeng commented Oct 15, 2024 •

edited

Loading

vercel bot commented Oct 15, 2024

lobehubbot commented Oct 15, 2024

codecov bot commented Oct 15, 2024 •

edited

Loading

hezhijie0327 commented Oct 15, 2024 •

edited

Loading

hezhijie0327 commented Oct 15, 2024 •

edited

Loading

LovelyGuYiMeng commented Oct 15, 2024

LovelyGuYiMeng commented Oct 15, 2024

lobehubbot commented Oct 15, 2024

hezhijie0327 commented Oct 16, 2024

LovelyGuYiMeng commented Oct 16, 2024

LovelyGuYiMeng commented Oct 16, 2024

lobehubbot commented Oct 16, 2024

vercel bot commented Oct 17, 2024 •

edited

Loading

lobehubbot commented Oct 17, 2024

lobehubbot commented Oct 17, 2024

💄 style: add qwen vision model & update qwen2.5 72b to 128k for siliconcloud #4380

💄 style: add qwen vision model & update qwen2.5 72b to 128k for siliconcloud #4380

Conversation

LovelyGuYiMeng commented Oct 15, 2024 • edited Loading

💻 变更类型 | Change Type

🔀 变更说明 | Description of Change

📝 补充信息 | Additional Information

vercel bot commented Oct 15, 2024

lobehubbot commented Oct 15, 2024

codecov bot commented Oct 15, 2024 • edited Loading

Codecov Report

hezhijie0327 commented Oct 15, 2024 • edited Loading

hezhijie0327 commented Oct 15, 2024 • edited Loading

LovelyGuYiMeng commented Oct 15, 2024

LovelyGuYiMeng commented Oct 15, 2024

lobehubbot commented Oct 15, 2024

hezhijie0327 commented Oct 16, 2024

LovelyGuYiMeng commented Oct 16, 2024

LovelyGuYiMeng commented Oct 16, 2024

lobehubbot commented Oct 16, 2024

vercel bot commented Oct 17, 2024 • edited Loading

lobehubbot commented Oct 17, 2024

lobehubbot commented Oct 17, 2024

LovelyGuYiMeng commented Oct 15, 2024 •

edited

Loading

codecov bot commented Oct 15, 2024 •

edited

Loading

hezhijie0327 commented Oct 15, 2024 •

edited

Loading

hezhijie0327 commented Oct 15, 2024 •

edited

Loading

vercel bot commented Oct 17, 2024 •

edited

Loading