microsoft/lida

Evaluation of HF Models with LIDA

Aperta

#41 aperta il 18 set 2023

 (9 commenti) (1 reazione) (0 assegnatari)Jupyter Notebook (378 fork)github user discovery
enhancementgood first issue

Metriche repository

Star
 (3253 stelle)
Metriche merge PR
 (Nessuna PR mergiata in 30 g)

Descrizione

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

Guida contributor