update requirements- Remove bitsandbytes dependency, update init pipeline-Disable 8-bit quantization

helper.py

@@ -46,13 +46,15 @@ def get_huggingface_api_key():
 MODEL_CONFIG = {
     "main_model": {
         "name": "meta-llama/Llama-3.2-3B-Instruct",
-        "dtype": torch.bfloat16,
+        # "dtype": torch.bfloat16,
+        "dtype": torch.float32,  # Use float32 for CPU
         "max_length": 512,
         "device": "cuda" if torch.cuda.is_available() else "cpu",
     },
     "safety_model": {
         "name": "meta-llama/Llama-Guard-3-1B",
-        "dtype": torch.bfloat16,
+        # "dtype": torch.bfloat16,
+        "dtype": torch.float32,  # Use float32 for CPU
         "max_length": 256,
         "device": "cuda" if torch.cuda.is_available() else "cpu",
     },

requirements.txt

@@ -2,7 +2,7 @@ accelerate==1.1.1
 aiofiles==23.2.1
 annotated-types==0.7.0
 anyio==4.6.2.post1
-bitsandbytes==0.45.0
+# bitsandbytes==0.45.0
 certifi==2024.8.30
 charset-normalizer==3.4.0
 click==8.1.7