Update app.py

app.py

@@ -1,63 +1,26 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+from transformers import GPT2Tokenizer, GPT2LMHeadModel
+import torch
 
-"""
-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")
+model = GPT2LMHeadModel.from_pretrained('/content/model/medical-chatbot')
+tokenizer = GPT2Tokenizer.from_pretrained('openai-community/gpt2-medium')
 
+def chat_with_bot(prompt):
+    if tokenizer.pad_token is None:
+        tokenizer.pad_token = tokenizer.eos_token
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+    # Tokenize the input
+    inputs = tokenizer(f"[INST] {prompt} \n[/INST]", return_tensors="pt", padding=True)
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+    length = 18 + len(prompt)
+    # Generate a response
+    with torch.no_grad():
+        outputs = inference.generate(inputs['input_ids'], attention_mask=inputs['attention_mask'],max_new_tokens=50, num_return_sequences=1, pad_token_id=tokenizer.pad_token_id)
 
-    messages.append({"role": "user", "content": message})
+    # Decode and return the response
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return response[length:]
 
-    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)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+iface = gr.Interface(fn=chat_with_bot, inputs="text", outputs="text")
+iface.launch()