app.py

import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "moonshotai/Kimi-K2-Instruct"

tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.float16,
    device_map="auto",
    trust_remote_code=True
)

def chat(prompt):
    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device)

    outputs = model.generate(
        input_ids=input_ids,
        max_new_tokens=512,
        do_sample=True,
        temperature=0.7,
        top_p=0.9
    )

    response = tokenizer.decode(outputs[0][input_ids.shape[-1]:], skip_special_tokens=True)
    return response.strip()

gr.Interface(fn=chat, inputs=gr.Textbox(lines=5, label="Prompt"), outputs="text").launch()