emiya111/EmiyaMind-Qwen3-1.7B-Wenyan-Full

import torch
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

adapter_id = "emiya111/EmiyaMind-Qwen3-1.7B-Wenyan-Full"
base_id = "Qwen/Qwen3-1.7B"

tokenizer = AutoTokenizer.from_pretrained(adapter_id)
base_model = AutoModelForCausalLM.from_pretrained(
    base_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
model = PeftModel.from_pretrained(base_model, adapter_id)
model.eval()

source = "环滁皆山也。其西南诸峰，林壑尤美。"
messages = [
    {
        "role": "system",
        "content": (
            "你是一名严谨的古汉语翻译专家。你的任务是把文言文翻译成通顺、准确的现代汉语，"
            "忠实保留原文的人名、地名、官名、时间、因果关系和语气，不增添原文没有的信息。"
        ),
    },
    {
        "role": "user",
        "content": f"请将下面的文言文翻译成现代汉语。只输出译文，不要解释。\n\n文言文：{source}",
    },
]
prompt = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False,
)
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.inference_mode():
    output = model.generate(
        **inputs,
        max_new_tokens=256,
        do_sample=False,
        repetition_penalty=1.05,
    )
result = tokenizer.decode(
    output[0, inputs["input_ids"].shape[1]:],
    skip_special_tokens=True,
)
print(result.strip())