fix(docker): resolve llama-cpp-python module import error

refactor(chat): migrate from transformers to llama-cpp-python using Qwen 3B

chore(docker): reintroduce llama-cpp-python pre-built wheel for faster build

fix(docker): increase gunicorn worker timeout to 120s

feat(nlp): optimize NLP model for CPU

fix(requirements.txt): Update file

feat(nlp): Optimize CPU usage for Hugging Face Spaces Free Tier

feat(nlp): reintroduce Qwen2.5-1.5B-Instruct model and migrate back to Transformers

fix(llama): fixed a bug with building llama

feat(llama): another attempt to integrate llama-cpp with the Qwen3-8B-Q4_K_M.gguf model

fix(llama): clear cache after llama

test(models): downloading models from transformers

fix(lama.cpp): Add prebuilt lamma.cpp to docker

fix(nlp): update Llama loading to use from_pretrained()

feat(python): Change Python version to 3.11-bullseye for llama-cpp-python prebuilt wheel

Fix(nlp): NLP model download and build fix

Fix(docker): repair building llama.cpp

Fix(docker): start of the model when building the Docker image

feat(nlp): add lama.cpp support for Qwen3-8B-Q5_K_M.gguf and download models

Fix commad to run in dockerfile

Fix python version

Fix dockerfile

Initial APP

initial commit