lm-sys / lm-sys/FastChat

Mixtral-8x7B-Instruct-v0.1: Chat arena vs local inference

Open
#2,850 2 comments 3 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
39.5k
Forks
4.8k
PR merge metrics
No merged PRs in 30d

Description

Here how I made Mixtral-8x7B-Instruct-v0.1 work using FastChat.vllm_worker.

- Python3.10 given that megablocks only works with Python3.10
- install vllm 0.2.4 version (newer versions of vLLM are having few issues like [#2219](https://github.com/vllm-project/vllm/issues/2219) , [#2229](https://github.com/vllm-project/vllm/issues/2229))
- checkpoints in .pt format
- cuda version >=12.1
- pip install megablocks

**Still I find the answers from the chat arena's Mixtral-8x7B-Instruct-v0.1 much better.**

```
curl --location 'http://$IP:8000/v1/chat/completions' \
--header 'Content-Type: application/json' \
--data '{
"model": "Mixtral",
"messages": [
{
"role": "user",

"content":"who are you?"

}
],
"temprature": 0.7,
"max_tokens": 1024,
"top_p":1
}'

```

Answer from local inference.

```
{
"id": "chatcmpl-GohBJuu5P6kXkDzU3BsCib",
"object": "chat.completion",
"created": 1703237717,
"model": "Mixtral",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": " I am an artificial intelligence assistant, designed to help answer questions, provide information, and assist with various tasks to make your life easier and more convenient."
},
"finish_reason": "stop"

}
],
"usage": {
"prompt_tokens": 540,
"total_tokens": 571,
"completion_tokens": 31
}
}
```

------
Answer from the Chat Arena.

Screenshot 2023-12-22 at 3 08 37 PM

------
Still have few questions

**_Is there anything that I'm still missing?_**
- I knew LLM are not going to produce the same result but still the answer I'm getting using my local inference are still having lesser quality compared to Arena.
- Is there any specific system prompt I need to use to get the right quality output?
- What is the average throughput of Mixtral-8x7B-Instruct-v0.1 model? Any information around same?

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with the FastChat.vllm_worker setup described in the issue, including Python 3.10, vLLM 0.2.4, Megablocks, CUDA, and the chat completions curl request. Compare the local Mixtral-8x7B-Instruct-v0.1 configuration and output with the Chat Arena example. Done would require identifying the missing configuration or explaining the quality and throughput difference, but the issue does not define a concrete fix or test.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai, backend
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.