TLLMC/g-1.1.0-mxfp4-fixed-2512

from transformers import pipeline

model_id = "./g-1.1.0-mxfp4-fixed-2512"  # 或本機目錄路徑

pipe = pipeline(
    "text-generation",
    model=model_id,
    device_map="auto",
    trust_remote_code=True,
)

messages = [
    {
        "role": "user",
        "content": "USER PROMPT HERE",
    },
]

prompt = pipe.tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
)

outputs = pipe(
    prompt,
    max_new_tokens=2048,
    do_sample=True,
    temperature=0.7,
    top_p=0.9,
    return_full_text=False,
)

print(outputs[0]["generated_text"])