replaced with my app.py file

app.py

@@ -1,64 +1,45 @@
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
 
+model_id = "MaxBlumenfeld/smollm2-135m-bootleg-instruct"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id)
+
+def generate_response(message, temperature=0.7, max_length=200):
+   prompt = f"Human: {message}\nAssistant:"
+   inputs = tokenizer(prompt, return_tensors="pt")
+   
+   with torch.no_grad():
+       outputs = model.generate(
+           inputs.input_ids,
+           max_length=max_length,
+           temperature=temperature,
+           do_sample=True,
+           pad_token_id=tokenizer.eos_token_id
+       )
+   
+   response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+   return response.split("Assistant:")[-1].strip()
+
+with gr.Blocks() as demo:
+   gr.Markdown("# SmolLM2 Bootleg Instruct Chat")
+   
+   with gr.Row():
+       with gr.Column():
+           message = gr.Textbox(label="Message")
+           temp = gr.Slider(minimum=0.1, maximum=2.0, value=0.7, label="Temperature")
+           max_len = gr.Slider(minimum=50, maximum=500, value=200, label="Max Length") 
+           submit = gr.Button("Send")
+           
+       with gr.Column():
+           output = gr.Textbox(label="Response")
+           
+   submit.click(
+       generate_response,
+       inputs=[message, temp, max_len],
+       outputs=output
+   )
 
 if __name__ == "__main__":
-    demo.launch()
+   demo.launch()