full prec

app.py

@@ -18,10 +18,8 @@ def load_model():
             model = AutoModelForCausalLM.from_pretrained(
                 "omi-health/sum-small", 
                 trust_remote_code=False,
-                torch_dtype=torch.float16,  # Half precision
                 device_map="auto"  # Let the library decide best device mapping
             )
-            print(f"Model loaded with float16 precision on GPU")
             print(f"GPU: {torch.cuda.get_device_name(0)}")
             print(f"Memory allocated: {torch.cuda.memory_allocated(0) / 1024**2:.2f} MB")
         else:

requirements.txt

@@ -2,3 +2,4 @@
 torch
 transformers>=4.36.0
 gradio>=3.50.0
+accelerate