microsoft/lida

Evaluation of HF Models with LIDA

オープン

#41 opened on 2023/09/18

 (9 件のコメント) (1 件のリアクション) (0 人の担当者)Jupyter Notebook (378 件のフォーク)github user discovery
enhancementgood first issue

Repository metrics

Stars
 (3,253 個のスター)
PR merge metrics
 (30d に merged PR はありません)

説明

What

Local models (e.g. LLAMA based models available via HuggingFace in the 7B or 13B size classes) offer multiple benefits (e.g., can be finetuned/adapted, run locally etc). While LIDA has been mostly tested with OpenAI models, more work is needed to test workflows and performance for HF models.

Work Items

  • Test a set of local HF models either directly with llmx or with LIDA, systematically document bugs and suggest fixes via PRs

コントリビューターガイド