Refactor to fit model recomended usage

app.py

@@ -1,6 +1,6 @@
 import gradio as gr
 from huggingface_hub import login
-from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, TextIteratorStreamer
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
 from threading import Thread
 import torch
 
@@ -20,15 +20,9 @@ def messages_for(python):
         {"role": "user", "content": user_prompt_for(python)}
     ]
 
-quant_config = BitsAndBytesConfig(
-    load_in_4bit=True,
-    bnb_4bit_use_double_quant=True,
-    bnb_4bit_compute_dtype=torch.bfloat16,
-    bnb_4bit_quant_type="nf4"
-)
-
 tokenizer = AutoTokenizer.from_pretrained(MODEL)
-model = AutoModelForCausalLM.from_pretrained(MODEL, device_map="auto", quantization_config=quant_config)
+model = AutoModelForCausalLM.from_pretrained(MODEL, torch_dtype=torch.bfloat16, device_map="auto")
+model.eval()
 streamer = TextIteratorStreamer(tokenizer)
 
 cplusplus = None

requirements.txt

@@ -1,4 +1,2 @@
-accelerate
-bitsandbytes
 torch
 transformers