test

app.py

@@ -7,9 +7,9 @@ import spaces
 loaded_models = {}
 
 # List of available models (update with your preferred models)
-models = ["gpt2", "gpt2-medium", "gpt2-large", "EleutherAI/gpt-neo-1.3B"]
-
+models = ["hanzla/gemma-2b-datascience-instruct-v5", "hanzla/gemma-2b-datascience-instruct-v4.5"]
 
+@spaces.GPU
 def load_model(model_name):
     if model_name not in loaded_models:
         print(f"Loading model: {model_name}")
@@ -23,10 +23,9 @@ def get_model_response(model_name, message):
     model, tokenizer = load_model(model_name)
     inputs = tokenizer(message, return_tensors="pt").to(model.device)
 
-    with torch.no_grad():
-        outputs = model.generate(**inputs, max_length=100, num_return_sequences=1, temperature=0.7)
+    outputs = model.generate(**inputs)
 
-    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    response = tokenizer.decode(outputs[0])
     return response