Update app.py

app.py

@@ -1,50 +1,57 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoTokenizer, AutoModelForCausalLM, TextIteratorStreamer
+import torch
+from threading import Thread
 
-"""
-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("HODACHI/EZO-Common-9B-gemma-2-it")
+MODEL_ID = "HODACHI/EZO-Common-9B-gemma-2-it"
+DTYPE = torch.bfloat16
 
+tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL_ID,
+    device_map="cuda",
+    torch_dtype=DTYPE,
+)
 
 def respond(
     message,
     history: list[tuple[str, str]],
-    system_message,
     max_tokens,
     temperature,
     top_p,
 ):
-    messages = []
-    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})
+    chat = []
+    for user, assistant in history:
+        chat.append({"role": "user", "content": user})
+        chat.append({"role": "assistant", "content": assistant})
+    chat.append({"role": "user", "content": message})
 
-    response = ""
+    prompt = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
+    inputs = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt").to(model.device)
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
+    streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
+    
+    generation_kwargs = dict(
+        input_ids=inputs,
+        max_new_tokens=max_tokens,
         temperature=temperature,
         top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+        do_sample=True,
+        streamer=streamer,
+    )
+    
+    thread = Thread(target=model.generate, kwargs=generation_kwargs)
+    thread.start()
 
-        response += token
+    response = ""
+    for new_text in streamer:
+        response += new_text
         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.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
+        gr.Slider(minimum=1, maximum=2048, value=150, 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,
@@ -56,6 +63,5 @@ demo = gr.ChatInterface(
     ],
 )
 
-
 if __name__ == "__main__":
     demo.launch()