chore(requirements): remove llama_cpp requirement from requirements.txt

chat_ui/app.py

@@ -1,13 +1,11 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
 import subprocess
 from huggingface_hub import hf_hub_download
 
 subprocess.run("pip install -V llama_cpp_python==0.3.1", shell=True)
-# Download GGUF model into HF Space storage
-
 from llama_cpp import Llama
 
+# Download GGUF model into HF Space storage
 model_path = hf_hub_download(
     repo_id="ft-lora/llama3.2-3b-gguf-q4km",
     filename="llama3.2-3b-instruct-finetuned.gguf"

chat_ui/requirements.txt

@@ -1,2 +1 @@
-llama-cpp-python==0.3.1
 gradio

requirements.txt

@@ -1,3 +1,2 @@
-llama-cpp-python==0.3.1
 gradio
 huggingface_hub