Skip to content

CodinjaoftheWorld/qlora_falcon_7b_finetuned_medical_chatbot

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

qlora_falcon_7b_finetuned_medical_chatbot

QLoRA Falcon 7B finetuned on Medical Q&A Chatbot

Related publication - https://medium.com/@gauravsaini.728/qlora-fine-tuning-of-falcon-7b-for-medical-chatbot-b3bdc75ffcd2

The above publication explored various advancements in Large Language Models (LLMs) and techniques to enhance their training efficiency. It delved into concepts such as gradient scaling, quantization, and mixed precision training, highlighting their importance in optimizing resource usage while maintaining model accuracy. Additionally, it examined methods like LoRA and QLoRA for fine-tuning models effectively. It also covered the implementation of fine-tuning of Flacon 7B LLM with QLoRA technique on the medical Q&A dataset. It also covers the techniques to improve the performance in subsequent rounds of fine-tuning.

About

QLoRA Falcon 7B finetuned on Medical Q&A

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published