app para avalição do modelo treinado

app.py

@@ -1,28 +1,20 @@
 import gradio as gr
-from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
+from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
 
 # Load model and tokenizer
-model_name = "unsloth/Llama-3.2-1B-Instruct-bnb-4bit"
-
-# Configure quantization
-bnb_config = BitsAndBytesConfig(
-    load_in_4bit=True,
-    bnb_4bit_use_double_quant=True,
-    bnb_4bit_quant_type="nf4",
-    bnb_4bit_compute_dtype=torch.float16
-)
+model_name = "unsloth/Llama-3.2-1B-Instruct"  # Use the non-quantized version
 
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(
     model_name,
-    quantization_config=bnb_config,
-    device_map="auto",
-    trust_remote_code=True
+    torch_dtype=torch.float32,
+    low_cpu_mem_usage=True,
+    device_map="cpu"
 )
 
 def generate_text(prompt, max_new_tokens, temperature):
-    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+    inputs = tokenizer(prompt, return_tensors="pt")
     
     with torch.no_grad():
         outputs = model.generate(

requirements.txt

@@ -2,7 +2,4 @@ huggingface_hub==0.25.2
 
 gradio
 transformers
-torch
-accelerate>=0.26.0
-bitsandbytes
-
+torch