Update app.py

app.py

@@ -1,64 +1,39 @@
-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")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    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]})
-
-    messages.append({"role": "user", "content": message})
-
-    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
-
-        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)",
-        ),
-    ],
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch, gradio as gr, re
+
+MODEL = "moonshotai/Kimi-K2-Instruct"
+tok = AutoTokenizer.from_pretrained(MODEL, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+        MODEL,
+        torch_dtype=torch.bfloat16,
+        device_map="auto",
+        load_in_4bit=True,
+        trust_remote_code=True
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+# ==== 3.  Helper: build a research prompt ====
+SYS_PROMPT = """You are Kimi-Research, a helpful research assistant.
+Given a topic, you MUST:
+1. Search the web for the latest findings (cite URLs).
+2. Summarize key points in ≤250 words.
+3. End with 3 follow-up questions."""
+
+def answer(topic, history):
+    chat = [{"role":"system", "content": SYS_PROMPT},
+            {"role":"user",   "content": f"Research topic: {topic}"}]
+    prompt = tok.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
+    inputs  = tok(prompt, return_tensors="pt").to(model.device)
+    outputs = model.generate(**inputs,
+                             max_new_tokens=512,
+                             do_sample=True,
+                             temperature=0.4,
+                             repetition_penalty=1.05)
+    reply = tok.decode(outputs[0][len(inputs.input_ids[0]):], skip_special_tokens=True)
+    return reply.strip()
+
+# ==== 4.  Gradio UI ====
+demo = gr.ChatInterface(fn=answer,
+                        title="Kimi-K2 Research Assistant",
+                        description="Type any research topic and get a concise report.",
+                        examples=["Neuro-symbolic AI", "Climate tipping points 2025"])
+demo.launch(debug=True, share=True)