Rolling back previous change: optimum-quanto is not applicable to pub…

Replaced quanto with optimum-quanto so HF-Waitress does not error out…

Updated transformers version from 4.44.0 to 4.45.2

removed llama-index dependencies

BUG FIX: default defined for use_flash_attention_2

added explanation-comment

1) Changed encoding to UTF-8 2) Removed dependencies: nvidia-cuda-run…

BUG FIX: Correctly displaying LLM name in InfoBox when swapping LLMs …

CUDA GPU cache emptied post response

1) BUG FIX: LLM_CHANGE_RELOAD_TRIGGER_SET correctly reset for llama.c…

various bug fixes

updated requirements to address deployment troubles

Tab-Title Change

Seperating CSS

Seperating CSS

Removed unnecessary print

Major update: Refactored /completions_stream to only redirect TextStr…

fetch_file_list_for_vector_db is now filepath agnostic

Cleaner code!

Code cleanup

Major styling update: 1) New universal font-family: Inter 2) New glas…

BUG FIX: HQQ quantization would error out if torch.dtype (dataType) w…

Removed unused imports in HF-Waitress server.

more spare code

BUG FIX: Removed test-prints for document-chunking that could sometim…

Refined health-check error reporting

Enhanced HF-Waitress LLM Management: Add new model_ids, search-filter…

Removed troublesome and unnecessary dependency install>=1.3.5

README update

README update