lm-sys / lm-sys/FastChat

Inconsistent use of model_path and model_id in gen_model_answer.py

Open
#3,026 1 comment 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

While generating model answers in `gen_model_answer.py` there is inconsistency in how the appropriate model adapter is being created:

- in some cases , `model_id` is used
https://github.com/lm-sys/FastChat/blob/9924687b67d62032641640bd245d682c4d2f025e/fastchat/llm_judge/gen_model_answer.py#L107

- in other cases, `model_name` is used . Note:
https://github.com/lm-sys/FastChat/blob/9924687b67d62032641640bd245d682c4d2f025e/fastchat/model/model_adapter.py#L197

**Fix**:

use one of `model_id` or `model_name` consistently

**Workaround:**

Ensure both `model_id` and `model_name` has the keyword needed to initialize correct adapter

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 in fastchat/llm_judge/gen_model_answer.py at the adapter creation around line 107, then compare it with the model adapter handling around line 197 in fastchat/model/model_adapter.py. Trace how model_id and model_name are used during model-answer generation. Done means adapter initialization uses one consistent identifier while preserving correct adapter selection for the documented workaround cases.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai
Issue type
Bug
Difficulty
2/5
Estimated time
1-3 hours
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
45/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.