GLM-4.7-Flash-REAP-50

vllm serve Akicou/GLM-4.7-Flash-REAP-50 \
    --tensor-parallel-size 2 \
    --trust-remote-code \
    --dtype bfloat16

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "Akicou/GLM-4.7-Flash-REAP-50",
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained("Akicou/GLM-4.7-REAP-50", trust_remote_code=True)

messages = [{"role": "user", "content": "Write a Python function to merge two sorted lists."}]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True)
outputs = model.generate(inputs.to(model.device), max_new_tokens=512, temperature=0.7)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))