Translation
Transformers
Safetensors
GGUF
llama
text-generation
minicpm
minicpm5
on-device
text-generation-inference
Instructions to use Caldalis/MiniTranslator-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Caldalis/MiniTranslator-2B with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("translation", model="Caldalis/MiniTranslator-2B")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Caldalis/MiniTranslator-2B") model = AutoModelForCausalLM.from_pretrained("Caldalis/MiniTranslator-2B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from Caldalis/MiniTranslator-2B: direct link, hf CLI and curl.
- Browser
- Download file 10.1 kB
-
https://huggingface.co/Caldalis/MiniTranslator-2B/resolve/main/README.md
- Command line
-
hf download hf://Caldalis/MiniTranslator-2B/README.md
-
curl -L -o README.md https://huggingface.co/Caldalis/MiniTranslator-2B/resolve/main/README.md
10.1 kB
| language: | |
| - zh | |
| - en | |
| - ja | |
| - ko | |
| - ar | |
| - de | |
| - fr | |
| - es | |
| - ru | |
| - bn | |
| - cs | |
| - et | |
| - fa | |
| - he | |
| - id | |
| - kn | |
| - ro | |
| - ta | |
| - te | |
| - tl | |
| - tr | |
| - uk | |
| library_name: transformers | |
| license: apache-2.0 | |
| base_model: openbmb/MiniCPM5-2B | |
| base_model_relation: finetune | |
| pipeline_tag: translation | |
| tags: | |
| - translation | |
| - minicpm | |
| - minicpm5 | |
| - gguf | |
| - on-device | |
| <p align="center"> | |
| 🤗 <a href="https://huggingface.co/Caldalis/MiniTranslator-2B"><b>Hugging Face</b></a> | | |
| 💾 <a href="https://huggingface.co/Caldalis/MiniTranslator-2B-GGUF"><b>GGUF</b></a> | |
| </p> | |
| <p align="center"> | |
| <img src="imgs/banner.png" alt="MiniTranslator-2B — multilingual translation, 2B parameters" width="100%"> | |
| </p> | |
| # MiniTranslator-2B | |
| ## Model Introduction | |
| MiniTranslator-2B is a 2B multilingual translation model built on | |
| [MiniCPM5-2B](https://huggingface.co/openbmb/MiniCPM5-2B). It supports translation | |
| among Chinese, English, and 20 additional languages, and follows translation | |
| instructions in both Chinese and English. The model is designed for general | |
| translation workloads as well as on-device and edge deployment. | |
| MiniTranslator-2B is released in BF16 and in four GGUF variants (F16 / Q8_0 / Q6_K / | |
| Q4_K_M), so the same model can run with transformers, vLLM, SGLang, or llama.cpp. | |
| ## Results | |
| All translation results use greedy decoding (`temperature=0`) and XCOMET (higher is | |
| better). Instruction-following results use the benchmark's rule-based scoring. | |
| ### Translation | |
|  | |
| MiniTranslator-2B is competitive with Hy-MT2-1.8B on FLORES-200, NTREX-128, and | |
| WMT24++, and leads on HardMTBench by 3.1 points. WMT25 long-form and structured | |
| content remains the largest gap to the 7B and 30B-A3B models. | |
| ### Instruction Following | |
|  | |
| ## Model Links | |
| | Model | Description | Download | | |
| |---|---|---| | |
| | MiniTranslator-2B | BF16 weights | [🤗 Model](https://huggingface.co/Caldalis/MiniTranslator-2B) | | |
| | MiniTranslator-2B-GGUF | F16 / Q8_0 / Q6_K / Q4_K_M | [🤗 Model](https://huggingface.co/Caldalis/MiniTranslator-2B-GGUF) | | |
| ## Translation Task Instruction Examples (Chinese-English Comparison) | |
| *Note: both `source_lang` and `target_lang` should use full language names. Use | |
| Chinese names in Chinese prompts and English names in English prompts.* | |
| | Type | Chinese prompt | English prompt | | |
| |---|---|---| | |
| | **Default Translation** | 将以下文本翻译为 `{target_lang}`,只输出译文:<br><br>`{source_text}` | Translate the following text into `{target_lang}`. Output only the translation:<br><br>`{source_text}` | | |
| | **Terminology** | *参考下面的翻译:*<br>`{text}` 翻译成 `{text}`<br>`{text}` 翻译成 `{text}`<br><br>将以下文本翻译为 `{target_lang}`,只输出译文:<br><br>`{source_text}` | *Reference the following translations:*<br>`{text}` translates to `{text}`<br>`{text}` translates to `{text}`<br><br>Translate the following text into `{target_lang}`. Output only the translation:<br><br>`{source_text}` | | |
| | **Style** | 请将以下文本翻译为 `{target_lang}`。<br>翻译风格要严格符合【**`{target_style}`**】<br><br>`{source_text}` | Please translate the following text into `{target_lang}`. The translation style must strictly conform to [**`{target_style}`**]:<br><br>`{source_text}` | | |
| | **Personalization** | *【待翻译文本】*<br>`{source_text}`<br><br>*【翻译任务】*<br>1、**`{user_preferences}`**<br>2、**`{user_preferences}`**<br>3、……<br>4、将【待翻译文本】翻译为 `{target_lang}`。 | *[Source Text]*<br>`{source_text}`<br><br>*[Translation Tasks]*<br>1. **`{user_preferences}`**<br>2. **`{user_preferences}`**<br>3. ...<br>4. Translate the [Source Text] into `{target_lang}`. | | |
| | **Delimiters** | 请将以下文本准确翻译为 `{target_lang}`。<br>你必须在译文中**保留等量的分隔符,绝对不可遗漏、转义或翻译该符号,并注意分隔符的位置**。<br><br>`{source_text}` | Please accurately translate the following text into `{target_lang}`.<br>You must **retain the exact same number of delimiters in the translation. Strictly do not omit, escape, or translate these symbols, and pay close attention to their placement**.<br><br>`{source_text}` | | |
| | **Structured Data** | *# 任务目标*<br>将下方 `{source_text}` 中的 `{format_type}` 格式数据翻译为 `{target_lang}`。<br><br>*# 严格约束*<br>1. **结构锁定**:绝对保持原有的 `{format_type}` 数据结构、缩进和层级完全不变。<br>2. **选择性翻译**:仅翻译面向用户展示的可见文本内容。<br>3. **禁止修改**:**严禁**翻译或更改任何代码标签、键名(Key)、变量占位符(如 `{{var}}`、`${var}`、`%s`、`%d` 等)或代码属性。<br><br>*# 数据输入*<br>`{source_text}` | *### Task*<br>Translate the user-facing text within the following `{format_type}` data into `{target_lang}`.<br><br>*### Strict Rules*<br>1. **Structure Preservation:** You MUST preserve the original `{format_type}` data structure, nesting, hierarchy, and indentation exactly as they are.<br>2. **Selective Translation:** Translate ONLY the visible, user-facing text content/values.<br>3. **Strict Non-Translation:** NEVER translate or alter code tags, keys, properties, object names, or variable placeholders. Leave them exactly in their original English/code form.<br><br>*### Source Data*<br>`{source_text}` | | |
| | **Background Information** | *【背景信息】*<br>`{background_text}`<br><br>请结合背景信息将以下文本翻译为 `{target_lang}`。<br><br>*【待翻译文本】*<br>`{source_text}` | *[Background Information]*<br>`{background_text}`<br><br>Please translate the following text into `{target_lang}`, taking the provided background information into consideration.<br><br>*[Source Text]*<br>`{source_text}` | | |
| --- | |
| ## Inference and Deployment | |
| Recommended decoding parameters. The model does not have a default system prompt. | |
| ```json | |
| { | |
| "temperature": 0, | |
| "top_p": 0.95, | |
| "max_tokens": 4096 | |
| } | |
| ``` | |
| Greedy decoding (`temperature=0`) is recommended for translation. If sampling is | |
| needed, use a low temperature (0.2–0.3) and `top_p=0.9`. | |
| Thinking mode is supported by the chat template but should be disabled for | |
| translation: pass `enable_thinking=False` in transformers, `--reasoning off` in | |
| llama.cpp, or `chat_template_kwargs: {"enable_thinking": false}` in an | |
| OpenAI-compatible request. | |
| ### transformers | |
| `transformers>=5.6.0` | |
| ```python | |
| import torch | |
| from transformers import AutoModelForCausalLM, AutoTokenizer | |
| model_path = "Caldalis/MiniTranslator-2B" | |
| tokenizer = AutoTokenizer.from_pretrained(model_path) | |
| model = AutoModelForCausalLM.from_pretrained( | |
| model_path, | |
| dtype=torch.bfloat16, | |
| device_map="auto", | |
| ) | |
| model.eval() | |
| prompt = "将以下文本翻译成英语,只输出译文:\n\n今天天气真好。" | |
| messages = [{"role": "user", "content": prompt}] | |
| inputs = tokenizer.apply_chat_template( | |
| messages, | |
| tokenize=True, | |
| add_generation_prompt=True, | |
| enable_thinking=False, | |
| return_tensors="pt", | |
| ).to(model.device) | |
| with torch.no_grad(): | |
| outputs = model.generate(**inputs, max_new_tokens=4096, do_sample=False) | |
| response = tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True) | |
| print(response) | |
| ``` | |
| ### vLLM | |
| ```bash | |
| vllm serve Caldalis/MiniTranslator-2B --tensor-parallel-size 1 | |
| ``` | |
| ### SGLang | |
| ```bash | |
| python3 -m sglang.launch_server --model Caldalis/MiniTranslator-2B --tp 1 | |
| ``` | |
| ### llama.cpp | |
| ```bash | |
| llama-server -m MiniTranslator-2B-Q4_K_M.gguf -c 4096 --reasoning off --port 8080 | |
| ``` | |
| ```bash | |
| curl http://127.0.0.1:8080/v1/chat/completions \ | |
| -H 'Content-Type: application/json' \ | |
| -d '{ | |
| "messages": [{"role": "user", "content": "将以下文本翻译成英语,只输出译文:\n\n今天天气真好。"}], | |
| "temperature": 0, | |
| "max_tokens": 4096 | |
| }' | |
| ``` | |
| On llama.cpp builds without `--reasoning`, omit the server flag and add | |
| `"chat_template_kwargs": {"enable_thinking": false}` to the request body. | |
| ## Quantization | |
| | File | Quantization | Size (bytes) | SHA-256 | | |
| |---|---|---:|---| | |
| | `MiniTranslator-2B-F16.gguf` | F16 | 5,039,006,496 | `236b69f8d40370ac390ff6f48283349d66318d654094a643d3641f148aa8e958` | | |
| | `MiniTranslator-2B-Q8_0.gguf` | Q8_0 | 2,679,710,496 | `5999502dd1e520b18fcfa5bade61b64b7b119fa991d16f15b816f4f3b46d1997` | | |
| | `MiniTranslator-2B-Q6_K.gguf` | Q6_K | 2,070,225,696 | `df7895713c691700c36b1db458a8998cb2ac8cd60e8cff1cb8976a3fe500dd93` | | |
| | `MiniTranslator-2B-Q4_K_M.gguf` | Q4_K_M | 1,561,318,176 | `e7ebfd5120803c59163ed0cb44725c1e43e97be8434b031474c36ef32a867114` | | |
| Weights are converted with `llama.cpp/convert_hf_to_gguf.py` and quantized with | |
| `llama-quantize`. See the GGUF model repository for conversion and usage details. | |
| ## Supported Languages | |
| | Language | Abbr. | Chinese Name | | |
| |---|---|---| | |
| | Chinese | zh | 中文 | | |
| | English | en | 英语 | | |
| | Japanese | ja | 日语 | | |
| | Korean | ko | 韩语 | | |
| | Arabic | ar | 阿拉伯语 | | |
| | German | de | 德语 | | |
| | French | fr | 法语 | | |
| | Spanish | es | 西班牙语 | | |
| | Russian | ru | 俄语 | | |
| | Bengali | bn | 孟加拉语 | | |
| | Czech | cs | 捷克语 | | |
| | Estonian | et | 爱沙尼亚语 | | |
| | Persian | fa | 波斯语 | | |
| | Hebrew | he | 希伯来语 | | |
| | Indonesian | id | 印尼语 | | |
| | Kannada | kn | 卡纳达语 | | |
| | Romanian | ro | 罗马尼亚语 | | |
| | Tamil | ta | 泰米尔语 | | |
| | Telugu | te | 泰卢固语 | | |
| | Filipino | tl | 菲律宾语 | | |
| | Turkish | tr | 土耳其语 | | |
| | Ukrainian | uk | 乌克兰语 | | |
| The base model supports additional languages beyond this list. Quality on | |
| low-resource directions varies and should be validated on in-domain data. | |
| ## License | |
| Released under the **Apache License 2.0**. This model is a derivative of | |
| [openbmb/MiniCPM5-2B](https://huggingface.co/openbmb/MiniCPM5-2B); see `NOTICE` for | |
| attribution. "MiniCPM" and any OpenBMB marks remain the property of | |
| their owners. | |