minor spelling mistakes

reducing the chunk size and chunk overlap

added repetition penalty.

changing model and adding temperature parameters

removed the demo chat function

removing examples

trying simple chat function

update app.py

using complete local code and loading llm through ctransformers.

handling max_new_token errors.

Update app.py

Update app.py

change embedding model and file path for pdf

change model file and using ctransformers directly instead of langchain.

using ctransformers instead of llama.cpp

Update app.py

Update app.py

Rename grado-test-3-huggingface-space.py to app.py