Update app.py

app.py

@@ -1,14 +1,12 @@
 import gradio as gr
-from safetensors import safe_open
-from transformers import AutoTokenizer
+from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
 
-# Load the tokenizer from the Hugging Face Hub (This will fetch the tokenizer)
+# Load the tokenizer from the Hugging Face Hub
 tokenizer = AutoTokenizer.from_pretrained("adarsh3601/my_gemma3_pt")
 
-# Load the safetensors model
-with safe_open("adapter_model.safetensors", framework="pt") as f:
-    model = f.load()
+# Load the model from Hugging Face Hub (Assuming you are using a transformer model here)
+model = AutoModelForCausalLM.from_pretrained("adarsh3601/my_gemma3_pt")
 
 # Function to generate response using the model
 def generate_response(input_text):
@@ -17,7 +15,7 @@ def generate_response(input_text):
     
     # Generate output using the model
     with torch.no_grad():  # Disable gradients for inference
-        outputs = model.generate(inputs['input_ids'])
+        outputs = model.generate(inputs['input_ids'], max_length=50)  # You can adjust max_length and other parameters
     
     # Decode the output and return it
     return tokenizer.decode(outputs[0], skip_special_tokens=True)