Update app.py

app.py

@@ -1,56 +1,18 @@
-import gradio as gr
-from unsloth import FastLanguageModel
-from transformers import AutoTokenizer, TextStreamer
+# Import necessary libraries
+from transformers import AutoModel, AutoTokenizer
 
 # Load the model and tokenizer
-model_name = "Rafay17/Llama3.2_1b_customModel2"  # Your custom model
-model, tokenizer = FastLanguageModel.from_pretrained(model_name)
-FastLanguageModel.for_inference(model)  # Enable the model for inference
+model_name = "Rafay17/Llama3.2_1b_customModle2"
+model = AutoModel.from_pretrained(model_name)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
 
-# Function to generate a response
-def generate_response(message, history, max_tokens, temperature, top_p):
-    # Prepare the labeled prompt for response generation
-    labeled_prompt = f"User Input: {message}\nResponse:"
+# Prepare your input text
+input_text = "Your input text goes here."
+inputs = tokenizer(input_text, return_tensors="pt")
 
-    # Tokenize the input
-    inputs = tokenizer(
-        [labeled_prompt],
-        return_tensors="pt",
-        padding=True,
-        truncation=True,
-        max_length=512,
-    ).to("cuda")
+# Forward pass to get model outputs
+with torch.no_grad():
+    outputs = model(**inputs)
 
-    # Generate the response
-    text_streamer = TextStreamer(tokenizer, skip_prompt=True)
-    response = ""
-    for token in model.generate(
-        input_ids=inputs.input_ids,
-        attention_mask=inputs.attention_mask,
-        streamer=text_streamer,
-        max_new_tokens=max_tokens,
-        temperature=temperature,
-        top_p=top_p,
-        pad_token_id=tokenizer.eos_token_id,
-    ):
-        response += token
-
-    return response
-
-
-# Define the Gradio interface
-demo = gr.Interface(
-    fn=generate_response,
-    inputs=[
-        gr.Textbox(lines=2, placeholder="Enter your message here..."),
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=512, value=64, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=1.0, value=0.7, label="Temperature"),
-        gr.Slider(minimum=0.1, maximum=1.0, value=0.9, label="Top-p (nucleus sampling)"),
-    ],
-    outputs=gr.Textbox(label="Chatbot Response"),
-    live=True
-)
-
-if __name__ == "__main__":
-    demo.launch()
+# Do something with the outputs
+print(outputs)