GLM-5.1-444B-A14B-REAP

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
    "0xSero/GLM-5.1-444B-A14B-REAP",
    device_map="auto",
    torch_dtype=torch.bfloat16,
    trust_remote_code=True,
)
tokenizer = AutoTokenizer.from_pretrained("0xSero/GLM-5.1-444B-A14B-REAP", trust_remote_code=True)

# IMPORTANT: GLM-5.1 is a thinking/chat model. Use the chat template.
messages = [{"role": "user", "content": "Hello"}]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True)
out = model.generate(inputs.to(model.device), max_new_tokens=128)
print(tokenizer.decode(out[0]))