lm-sys / lm-sys/FastChat

How to run a model that isn't vicuna?

Open
#2,611 2 comments 0 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

I have a directory full of models and when running through the readme.md it downloaded a the vicuna model to .cache/huggingface/hub/ which was not to useful to me especially when the line
'''
python3 -m fastchat.serve.cli --model-path lmsys/fastchat-t5-3b-v1.0
'''
seems to imply that the model will be loaded to the lmsys

I've tried various methods. but cannot seem to load the model that I want, located at ~/ai/data/models/mistralai_Mistral-7B-v0.1/

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 README instructions and the fastchat.serve.cli command shown in the issue, then compare them with the reported local path ~/ai/data/models/mistralai_Mistral-7B-v0.1/. Done means the documentation clearly explains how to run a local model and what the lmsys/fastchat-t5-3b-v1.0 argument does.

Written by the indexing model from the issue text.

Assessment

Tech stack
huggingface, python
Domain
ai, documentation, machine-learning
Issue type
Documentation
Difficulty
2/5
Estimated time
1-3 hours
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.