Variable65536/minicpm5-1b-immersive-translate

pip install transformers torch accelerate

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = "Variable65536/minicpm5-immersive-translate"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained(model_path)

SYSTEM_PROMPT = """You are a professional Chinese native translator who needs to fluently translate text into Chinese.

## Translation Rules
1. Output only the translated content, without explanations or additional content (such as "Here's the translation:" or "Translation as follows:")
2. The returned translation must maintain exactly the same number of paragraphs and format as the original text
3. If the text contains HTML tags, consider where the tags should be placed in the translation while maintaining fluency
4. For content that should not be translated (such as proper nouns, code, etc.), keep the original text.
5. If input contains %%, use %% in your output, if input has no %%, don't use %% in your output

## OUTPUT FORMAT:
- **Single paragraph input** → Output translation directly (no separators, no extra text)
- **Multi-paragraph input** → Use %% as paragraph separator between translations
"""

# 单段输入
user_input = "Translate to Chinese (output translation only):\n\nThe committee approved the proposal after extensive deliberation."

messages = [
    {"role": "system", "content": SYSTEM_PROMPT},
    {"role": "user", "content": user_input},
]

input_ids = tokenizer.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_tensors="pt",
    return_dict=False,
).to(model.device)

outputs = model.generate(
    input_ids,
    max_new_tokens=512,
    temperature=0.2,
    top_p=0.9,
    do_sample=True,
)

result = tokenizer.decode(outputs[0][input_ids.shape[-1]:], skip_special_tokens=True)
print(result)
# 输出：委员会经过充分讨论后批准了该提案。

user_input = """Translate to Chinese:

## Installation

Run `pip install minicpm` to install the package.

%%

## Usage

See the <a href="https://github.com/OpenBMB/MiniCPM">repo</a> for examples.
"""

You are a professional Chinese native translator who needs to fluently translate text into Chinese.

## Translation Rules
1. Output only the translated content, without explanations or additional content (such as "Here's the translation:" or "Translation as follows:")
2. The returned translation must maintain exactly the same number of paragraphs and format as the original text
3. If the text contains HTML tags, consider where the tags should be placed in the translation while maintaining fluency
4. For content that should not be translated (such as proper nouns, code, etc.), keep the original text.
5. If input contains %%, use %% in your output, if input has no %%, don't use %% in your output

## OUTPUT FORMAT:
- **Single paragraph input** → Output translation directly (no separators, no extra text)
- **Multi-paragraph input** → Use %% as paragraph separator between translations

Translate to Chinese (output translation only):

{英文原文}

Translate to Chinese:

{英文段落 1}

%%

{英文段落 2}

pip install vllm
python -m vllm.entrypoints.openai.api_server \
    --model Variable65536/minicpm5-immersive-translate \
    --served-model-name minicpm5-immersive \
    --port 8000 \
    --dtype float16 \
    --max-model-len 4096

@misc{minicpm5,
  title={MiniCPM5},
  author={OpenBMB},
  year={2025},
  howpublished={\url{https://huggingface.co/openbmb/MiniCPM5-1B}}
}