Stable LM 3B 24-hours Hackathon

Start

Summarizes legislation and allows you to ask questions from it.Helpful for lawyers & their clients.

LegalLLM

Mehrdad Esmaeili

Stas

StableLM-tuned-alpha-3b was finetuned with lit-gpt repo lora method. This performed considerably better then the original model. 

Subject Matter ROUGH score for chatgpt summarization is 8/10
Subject Matter ROUGH score for legalLLM is 3/10
Subject Matter ROUGH score for stableLM-tuned-alpha-3b is 0/10

Considering gpt3 was 175B and chatgpt is most likely bigger, the fact that legalLLM could score 3 is significant

Training was done with lighteval/legal-summarization dataset. look at attached github repo for fine-tunning parameters. 
This fintuned model is uploaded huggingface under mehrdad-es/legalLLM-hf
The github repo shows how to create your gradio app to chat with the model. It is recommended to get a10 46GB ram system. 


StableLM-tuned-alpha-3b was finetuned with lit-gpt repo lora method on legal summarization dataset

"LegalLLM team on Stable LM 3B 24-hours Hackathon Hackathon"

Team Idea

Submission