rkingzhong/qwen2.5-0.5b-classical-chinese-trans

This model mainly focuses on Classical Chinese translation.

Usage

model_name = "rkingzhong/qwen2.5-0.5b-classical-chinese-trans"

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "子曰：“学而时习之，不亦说乎？有朋自远方来，不亦乐乎？人不知而不愠，不亦君子乎？"

messages = [
        {"role": "system", "content": "麻烦帮我翻译下面的文言文，不要出现互联网中的违禁词。"},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(
        **model_inputs,
        max_new_tokens=512
    )
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]

    print(response)