lm-sys / lm-sys/FastChat

Learderboard category/filter by model size

Open
#3,544 0 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

On those that tell their "size", it would be interesting to have a category or filter "size".

Additionally, I would say to always have the overall top 3 (for comparison) and then the filter.

For those filters, maybe a "mini" up to a few B, then the small ones up to 10B, some in-between... then those up to 100B (?) and after that (or those that don't show), they go all in the overall one.

There are some smaller models as powerful as the flagship ones (considering size), but might be "buried" outside the top ones multiple times their size.

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

No file, test, or entry point is named. Start by locating the leaderboard implementation and the model metadata used for displayed size, then confirm how rankings and filters are assembled. Done should include size-based categories or filtering while preserving the overall top three for comparison, with clear handling for missing sizes.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.