Kimi-K2.5-PRISM-REAP-72

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
    "0xsero/Kimi-K2.5-PRISM-REAP-72",
    trust_remote_code=True,
    dtype=torch.bfloat16,
    device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained(
    "0xsero/Kimi-K2.5-PRISM-REAP-72",
    trust_remote_code=True,
)

messages = [{"role": "user", "content": "What is the capital of France?"}]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", thinking=False)
inputs = inputs.to(model.device)

outputs = model.generate(inputs, max_new_tokens=512, temperature=0.6, do_sample=True)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))