docs: full English model card from Index-Translate technical report

README.md

@@ -1,16 +1,94 @@
 ---
-license: other
+license: apache-2.0
 tags:
 - translation
 - index
 ---
 
-# Index-MT-2B
+# Index-Translate-2B
 
-通用翻译模型（英/日/中互译），网页 translate 页默认 2B。
+[![Demo](https://img.shields.io/badge/Demo-Online-orange.svg)](https://index-translate.bilibili.com/)
+[![Code](https://img.shields.io/badge/GitHub-Index--Translate-yellow.svg)](https://github.com/bilibili/Index-Translate)
+[![License](https://img.shields.io/badge/License-Apache--2.0-lightgrey.svg)](https://github.com/bilibili/Index-Translate/blob/main/LICENSE)
 
-在线体验：https://index-translate.bilibili.com （B站 Index-Translate 系列线上服务同款权重）。
+**Index-Translate-2B** is the 2B-parameter multilingual text translation model of the **Index-Translate** family, built on the Qwen3.5 backbone. It supports **148 languages** with multilingual instruction following — terminology, formatting, style, structure, and output-length constraints — and powers the translate page of the [online demo](https://index-translate.bilibili.com/).
 
-Base: Qwen3.5 系列。推理：vLLM 直接 `vllm serve` 本目录即可（safetensors + tokenizer 齐全）。
+> 📄 Technical report: *Index-Translate: A Multilingual Translation Model Family — Text, Speech, Controlled Dubbing, and Long-Document Translation* (Index LLM Team, September 2026)
+>
+> 💻 Code, quickstarts, browser extension & video-dubbing pipeline: [github.com/bilibili/Index-Translate](https://github.com/bilibili/Index-Translate)
 
-> Model card 草稿，待补充评测数据与详细训练信息。
+## Highlights
+
+- **148 languages** with instruction following: general translation, constrained translation (terminology, structure, style, context), and meme/internet-culture translation in a single checkpoint.
+- **Training recipe**: multilingual mid-training (general + monolingual + parallel + pivot-organized data) → specialist SFT (general / instruction / meme experts) → RL with judged rewards (GRPO; XCOMET-XXL + adequacy gates for general translation, Rubric-as-Reward for instruction following) under RIVAL adversarial judge supervision → **parameter interpolation** (model soup, general : instruction : meme = 0.8 : 0.1 : 0.1) → targeted **multi-teacher on-policy distillation (MOPD)** for remaining weaknesses.
+- **262,144-token context window**, greedy decoding recommended.
+- Larger sibling: [IndexTeam/Index-Translate-9B](https://huggingface.co/IndexTeam/Index-Translate-9B).
+
+## Benchmarks
+
+Text translation (Table 4 of the report; WMT26 judge on a 0–100 scale, others 0–1):
+
+| Model | FLORES COMET-22 | WMT24++ COMET-22 | WMT26 Judge | instTrans IFscore | IFMTBench IFscore | Vertical mean | MEME |
+|---|---|---|---|---|---|---|---|
+| **Index-Translate-2B** | 0.8655 | 0.8489 | 60.26 | 0.7569 | 0.7584 | 0.8377 | 0.6443 |
+| Index-Translate-9B | **0.8789** | 0.8601 | 75.35 | **0.8209** | 0.8760 | 0.8451 | **0.7387** |
+| Hy-MT2-7B | 0.8747 | 0.8593 | 60.51 | 0.6079 | 0.8741 | 0.8335 | 0.5139 |
+| Hy-MT2-30B-A3B | 0.8787 | **0.8624** | 66.81 | 0.6415 | 0.9029 | **0.8459** | 0.5812 |
+| TranslateGemma-12B | 0.8732 | 0.8524 | — | 0.3068 | 0.2892 | 0.8347 | 0.4281 |
+| Qwen3.5-2B (base) | 0.6983 | 0.6933 | 32.11 | 0.2431 | 0.3836 | 0.7557 | 0.2062 |
+
+The 2B model outperforms Hy-MT2-1.8B on all metrics available for both models.
+
+Vertical-domain translation (COMET-22; GuoFeng uses document-COMET):
+
+| Model | OPUS-Books | Biomedical | MTNT | MuST-Cinema | GuoFeng |
+|---|---|---|---|---|---|
+| **Index-Translate-2B** | 0.7845 | 0.8635 | 0.8132 | 0.8930 | **0.8345** |
+| Index-Translate-9B | 0.8010 | 0.8674 | 0.8246 | **0.8979** | **0.8345** |
+
+General capabilities (answer accuracy %): C-Eval 42.6 / GPQA-Diamond 27.4 / INCLUDE 39.1 / MMMLU 42.7.
+
+## Usage
+
+```bash
+vllm serve IndexTeam/Index-Translate-2B --served-model-name Index-Translate-2B --port 8000
+```
+
+```python
+from openai import OpenAI
+
+client = OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY")
+resp = client.chat.completions.create(
+    model="Index-Translate-2B",
+    messages=[{"role": "user", "content": "Translate the following text into English:\n\n你好，世界！"}],
+    temperature=0,
+)
+print(resp.choices[0].message.content)
+```
+
+Transformers and SGLang quickstarts: [inference/llm](https://github.com/bilibili/Index-Translate/tree/main/inference/llm).
+
+## Model family
+
+| Model | Sizes | Task |
+|---|---|---|
+| **Index-Translate** | [2B](https://huggingface.co/IndexTeam/Index-Translate-2B) / [9B](https://huggingface.co/IndexTeam/Index-Translate-9B) | Multilingual text translation & translation instructions |
+| Index-Echo S2TT | [2B](https://huggingface.co/IndexTeam/Index-Echo-S2TT-2B) / [9B](https://huggingface.co/IndexTeam/Index-Echo-S2TT-9B) | Speech-to-text translation |
+| Index-Echo S2ST | [2B](https://huggingface.co/IndexTeam/Index-Echo-S2ST-2B) / [9B](https://huggingface.co/IndexTeam/Index-Echo-S2ST-9B) | Speech-to-speech translation with voice conditioning |
+| Index-Homura | [2B](https://huggingface.co/IndexTeam/Index-Homura-2B) / [9B](https://huggingface.co/IndexTeam/Index-Homura-9B) | Syllable-controlled translation (dubbing) |
+| Index-NaitiveLong (NaiLong) | [2B](https://huggingface.co/IndexTeam/Index-Nailong-2B) / [9B](https://huggingface.co/IndexTeam/Index-Nailong-9B) | Long-document translation |
+
+## Citation
+
+```bibtex
+@techreport{indextranslate2026,
+  title={Index-Translate: A Multilingual Translation Model Family --- Text, Speech, Controlled Dubbing, and Long-Document Translation},
+  author={Index LLM Team},
+  year={2026},
+  month={September}
+}
+```
+
+## License
+
+Apache-2.0.