Update app.py

app.py

@@ -1,70 +1,83 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from peft import PeftModel
 
+# ===== MODEL LOAD=====
+BASE_MODEL = "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B"
+LORA_PATH = "./deepseek-lab-assistant"
 
+tokenizer = AutoTokenizer.from_pretrained(
+    BASE_MODEL,
+    trust_remote_code=True
+)
+tokenizer.pad_token = tokenizer.eos_token
+
+model = AutoModelForCausalLM.from_pretrained(
+    BASE_MODEL,
+    torch_dtype=torch.float16,
+    device_map="auto",
+    trust_remote_code=True
+)
+
+model = PeftModel.from_pretrained(model, LORA_PATH)
+model.eval()
+
+
+# ===== CHAT FUNCTION =====
 def respond(
     message,
-    history: list[dict[str, str]],
+    history,
     system_message,
     max_tokens,
     temperature,
     top_p,
-    hf_token: gr.OAuthToken,
 ):
-    """
-    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(token=hf_token.token, model="openai/gpt-oss-20b")
+    # history = [{"role": "user"/"assistant", "content": "..."}]
+
+    prompt = system_message + "\n\n"
 
-    messages = [{"role": "system", "content": system_message}]
+    for h in history:
+        prompt += f"{h['role'].capitalize()}: {h['content']}\n"
 
-    messages.extend(history)
+    prompt += f"User: {message}\nAssistant:"
 
-    messages.append({"role": "user", "content": message})
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
 
-    response = ""
+    with torch.no_grad():
+        output = model.generate(
+            **inputs,
+            max_new_tokens=max_tokens,
+            temperature=temperature,
+            top_p=top_p,
+            do_sample=temperature > 0,
+        )
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
+    text = tokenizer.decode(output[0], skip_special_tokens=True)
 
-        response += token
-        yield response
+    if "Assistant:" in text:
+        text = text.split("Assistant:")[-1].strip()
 
+    return text
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+
+# ===== GRADIO UI =====
 chatbot = gr.ChatInterface(
     respond,
     type="messages",
     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.Textbox(
+            value="You are a helpful lab assistant. Explain ideas clearly. Do not rush to final answers.",
+            label="System message",
         ),
+        gr.Slider(1, 1024, value=256, step=1, label="Max new tokens"),
+        gr.Slider(0.0, 1.5, value=0.3, step=0.05, label="Temperature"),
+        gr.Slider(0.1, 1.0, value=0.9, step=0.05, label="Top-p"),
     ],
 )
 
 with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
     chatbot.render()
 
-
 if __name__ == "__main__":
     demo.launch()