Update app.py

app.py

@@ -1,11 +1,12 @@
+import torch
 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")
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
+def load_model():
+    model_name = "Qwen/Qwen2.5-Math-1.5B-Instruct"
+    model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    return model, tokenizer
 
 def respond(
     message,
@@ -16,49 +17,40 @@ def respond(
     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]})
-
+    
+    for user_msg, bot_reply in history:
+        messages.append({"role": "user", "content": user_msg})
+        if bot_reply:
+            messages.append({"role": "assistant", "content": bot_reply})
+    
     messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
+    
+    text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+    model_inputs = tokenizer([text], return_tensors="pt").to("cuda")
+    
+    generated_ids = model.generate(
+        **model_inputs,
+        max_new_tokens=max_tokens,
         temperature=temperature,
         top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
+    )
+    
+    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+    return response
 
+# Load model and tokenizer
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model, tokenizer = load_model()
 
-"""
-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)",
-        ),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
     ],
 )
 
-
 if __name__ == "__main__":
     demo.launch()