Spaces:

darpan-jain

/

llm-chat

like 0

Runtime error

I am hosting a fine-tuned with distillation model - Alpaca trained on data from LLaMa. Currently limited to a chat functionality (due to limited testing), I want to expand this to a project where it can be used for specific tasks like subject-specific QA and implement a small online learning pipeline.

Getting access to a GPU for running inference for this purpose will greatly help this effort and also help me showcase my capabilities in NLP.