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_zh.md from Caldalis/MiniTranslator-2B: direct link, hf CLI and curl.
- Browser
- Download file 9.63 kB
-
https://huggingface.co/Caldalis/MiniTranslator-2B/resolve/main/README_zh.md
- Command line
-
hf download hf://Caldalis/MiniTranslator-2B/README_zh.md
-
curl -L -o README_zh.md https://huggingface.co/Caldalis/MiniTranslator-2B/resolve/main/README_zh.md
9.63 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 — 多语种翻译,2B 参数" width="100%"> | |
| </p> | |
| # MiniTranslator-2B | |
| ## 模型介绍 | |
| MiniTranslator-2B 是基于 [MiniCPM5-2B](https://huggingface.co/openbmb/MiniCPM5-2B) 的 | |
| 2B 多语种翻译模型,支持中文、英文及另外 20 种语言之间的互译,并能遵循中英文翻译 | |
| 指令。模型面向通用翻译场景,也可用于端侧和边缘设备部署。 | |
| MiniTranslator-2B 提供 BF16 权重与四档 GGUF(F16 / Q8_0 / Q6_K / Q4_K_M),可在 | |
| transformers、vLLM、SGLang 与 llama.cpp 上运行。 | |
| ## 评测结果 | |
| 翻译结果均为贪心解码(`temperature=0`)下的 XCOMET 分数(越高越好);指令遵循结果 | |
| 采用各基准的规则打分。 | |
| ### 翻译 | |
|  | |
| MiniTranslator-2B 在 FLORES-200、NTREX-128 与 WMT24++ 上与 Hy-MT2-1.8B 基本持平, | |
| HardMTBench 领先 3.1 分;WMT25 的长文与结构化内容是相对 7B/30B-A3B 的主要差距。 | |
| ### 指令遵循 | |
|  | |
| ## 模型链接 | |
| | 模型 | 说明 | 下载 | | |
| |---|---|---| | |
| | MiniTranslator-2B | BF16 权重 | [🤗 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) | | |
| ## 翻译任务指令示例(中英对照) | |
| *说明:以下示例中的 `source_lang` 与 `target_lang` 应使用完整语言名称;中文提示词 | |
| 用中文名,英文提示词用英文名。* | |
| | 类型 | 中文提示词 | 英文提示词 | | |
| |---|---|---| | |
| | **默认翻译** | 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}` | | |
| | **术语** | *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}` | | |
| | **风格** | 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}` | | |
| | **个性化** | *【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}`. | | |
| | **分隔符** | 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}` | | |
| | **结构化数据** | *# 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}` | | |
| | **背景信息** | *【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}` | | |
| --- | |
| ## 推理与部署 | |
| 推荐解码参数如下。模型没有默认 system prompt。 | |
| ```json | |
| { | |
| "temperature": 0, | |
| "top_p": 0.95, | |
| "max_tokens": 4096 | |
| } | |
| ``` | |
| 翻译建议使用贪心解码(`temperature=0`);如需采样,使用较低温度(0.2–0.3)与 | |
| `top_p=0.9`。 | |
| chat template 支持思考模式,但翻译时应关闭:transformers 传 | |
| `enable_thinking=False`,llama.cpp 加 `--reasoning off`,OpenAI 兼容请求传 | |
| `chat_template_kwargs: {"enable_thinking": false}`。 | |
| ### 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 | |
| }' | |
| ``` | |
| 不支持 `--reasoning` 的 llama.cpp 构建,去掉该参数,并在请求体加 | |
| `"chat_template_kwargs": {"enable_thinking": false}`。 | |
| ## 量化 | |
| | 文件 | 量化 | 大小(字节) | 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` | | |
| 权重由 `llama.cpp/convert_hf_to_gguf.py` 转换,并用 `llama-quantize` 量化;转换与 | |
| 使用细节见 GGUF 模型仓库。 | |
| ## 支持语种 | |
| | 语言 | 缩写 | 中文名 | | |
| |---|---|---| | |
| | 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 | | |
| 基座模型还支持上表之外的语言;低资源方向的质量存在波动,建议在业务数据上验证。 | |
| ## 许可证 | |
| 以 **Apache License 2.0** 发布。本模型是 | |
| [openbmb/MiniCPM5-2B](https://huggingface.co/openbmb/MiniCPM5-2B) 的派生模型, | |
| 署名见 `NOTICE`。"MiniCPM" 名称及 OpenBMB 相关标识归其所有者。 | |