Update app.py

app.py

@@ -1,36 +1,26 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-from transformers import AutoTokenizer
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
-# Set the model name and initialize the InferenceClient and tokenizer
-model_name = "PierreJousselin/lora_model"  # Replace with your model's name
-client = InferenceClient(model_name)
+# Load the model and tokenizer from Hugging Face
+model_name = "your_huggingface_model_name"  # Replace with your model's name or path
+model = AutoModelForCausalLM.from_pretrained(model_name)
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 
-# Define a function to interact with the model
-def chat_with_model(input_text):
-    # Tokenize the input text
-    inputs = tokenizer(input_text, return_tensors="pt", truncation=True, padding=True, max_length=512)
-    inputs["pad_token_id"] = tokenizer.pad_token_id  # Set the pad token ID
-    # Send the request to the Hugging Face Inference API
-    result = client.text_generation(
-        prompt=inputs["input_ids"].tolist(),  # Send tokenized input
-    )
+# Define the chat function
+def chat_with_model(user_input):
+    # Encode the input
+    inputs = tokenizer.encode(user_input + tokenizer.eos_token, return_tensors="pt")
     
-    # Decode the generated text back to a readable format
-    response = tokenizer.decode(result[0]["generated_text"], skip_special_tokens=True)
+    # Generate a response from the model
+    outputs = model.generate(inputs, max_length=1000, pad_token_id=tokenizer.eos_token_id)
+    
+    # Decode the model's output
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
     
     return response
 
-# Set up the Gradio interface
-interface = gr.Interface(
-    fn=chat_with_model,
-    inputs=[gr.Textbox(lines=5, placeholder="Enter your text here...", label="Input Text")],
-    outputs=gr.Textbox(lines=5, label="Response"),
-    title="Hugging Face Chatbot",
-    description="A simple chatbot powered by Hugging Face and InferenceClient."
-)
+# Set up Gradio interface
+iface = gr.Interface(fn=chat_with_model, inputs="text", outputs="text", live=True)
 
-# Launch the Gradio app
-if __name__ == "__main__":
-    interface.launch()
+# Launch the interface
+iface.launch()