Update app.py

app.py

@@ -1,49 +1,38 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoModelForCausalLM, AutoTokenizer
+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_name = "INSAIT-Institute/MamayLM-Gemma-2-9B-IT-v0.1"  
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, 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 respond(message, chat_history, system_message, max_new_tokens, temperature, top_p):
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+    prompt = f"{system_message.strip()}\n"
+    for user, bot in chat_history:
+        prompt += f"User: {user}\nAssistant: {bot}\n"
+    prompt += f"User: {message}\nAssistant:"
 
-    messages.append({"role": "user", "content": message})
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+    output = model.generate(
+        **inputs,
+        max_new_tokens=int(max_new_tokens),
+        pad_token_id=tokenizer.eos_token_id,
+        do_sample=True,
+        temperature=float(temperature),
+        top_p=float(top_p),
+        eos_token_id=tokenizer.eos_token_id,
+    )
+    decoded = tokenizer.decode(output[0], skip_special_tokens=True)
 
-    response = ""
+    response = decoded.split("Assistant:")[-1].strip().split("User:")[0].strip()
+    return 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
+def clear_fn():
+    return None
 
-        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(
+chat = gr.ChatInterface(
     respond,
     additional_inputs=[
         gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
@@ -57,8 +46,16 @@ demo = gr.ChatInterface(
             label="Top-p (nucleus sampling)",
         ),
     ],
+    examples=[
+        ["Привіт!"],
+        ["Хто такий Пес Патрон?"],
+    ],
+    title="💬 Chat with MamayLM",
+    description="A multi-turn chat interface for MamayLM-v0,1-9B with configurable parameters.",
+    theme="soft",
+    retry_btn="🔄 Retry",
+    undo_btn="↩️ Undo",
+    clear_btn="🗑️ Clear Chat",
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+chat.launch()