Update app.py

app.py

@@ -4,17 +4,19 @@ import torch
 from peft import PeftModel, PeftConfig
 base_model = "TinyPixel/Llama-2-7B-bf16-sharded"
 tuned_adapter = "newronai/llama-2-7b-QLoRA-Trial1"
-bnb_config = BitsAndBytesConfig(
-    load_in_4bit=True,
-    bnb_4bit_quant_type="nf4",
-    bnb_4bit_compute_dtype=torch.float16,
-)
+# bnb_config = BitsAndBytesConfig(
+#     load_in_4bit=True,
+#     bnb_4bit_quant_type="nf4",
+#     bnb_4bit_compute_dtype=torch.float16,
+# )
+# bnb_config = BitsAndBytesConfig()
 
 
 config = PeftConfig.from_pretrained(tuned_adapter)
 model = AutoModelForCausalLM.from_pretrained(base_model,
                                              use_cache="cache",
-                                             quantization_config=bnb_config
+                                             
+                                             # quantization_config=bnb_config
                                             )
 
 model = PeftModel.from_pretrained(model, tuned_adapter)