Update app.py

app.py

@@ -1,64 +1,35 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoTokenizer, AutoModelForCausalLM, TextStreamer
+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_id = "mistralai/Mistral-7B-Instruct"
 
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+def chat(prompt, history=[]):
+    system_prompt = "You are a helpful AI assistant."
+    full_prompt = system_prompt + "\n"
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+    for user, bot in history:
+        full_prompt += f"User: {user}\nAssistant: {bot}\n"
+    full_prompt += f"User: {prompt}\nAssistant:"
 
-    messages.append({"role": "user", "content": message})
+    inputs = tokenizer(full_prompt, return_tensors="pt").to(model.device)
+    streamer = TextStreamer(tokenizer)
 
-    response = ""
+    output = model.generate(
+        **inputs,
+        max_new_tokens=300,
+        do_sample=True,
+        temperature=0.7,
+        top_p=0.95,
+        pad_token_id=tokenizer.eos_token_id
+    )
 
-    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
+    decoded = tokenizer.decode(output[0], skip_special_tokens=True)
+    response = decoded.split("Assistant:")[-1].strip()
+    history.append((prompt, response))
+    return response, history
 
-        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()
+gr.ChatInterface(chat, title="Mistral Chatbot").launch()