rr19tech/llama_index

Adding repetition penalty

Adjusted temperature and sample params

Adjusted the system prompt for structured output

Updated schema_str

Update app.py

Updated to add a new structured output method

Update app.py

Updated prompt

Reverted

Updated

Updated max_length

Updating max length

Update app.py

Adding some thread optimizations

Update app.py

Update app.py

Update app.py

Updated

Update app.py

Updated

Updated

Update app.py

Update app.py

Update app.py

Updated

Updated

Updated path

Updated

Updated

Updated to onnx runtime

Updated

Updated n_ctx

Update Dockerfile

Created app.py

Updated

Created a docker file

initial commit