Instructions to use tencent/Hy-MT2-1.8B-2Bit-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use tencent/Hy-MT2-1.8B-2Bit-GGUF with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="tencent/Hy-MT2-1.8B-2Bit-GGUF", filename="Hy-MT2-1.8B-2Bit.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use tencent/Hy-MT2-1.8B-2Bit-GGUF with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf tencent/Hy-MT2-1.8B-2Bit-GGUF # Run inference directly in the terminal: llama-cli -hf tencent/Hy-MT2-1.8B-2Bit-GGUF
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf tencent/Hy-MT2-1.8B-2Bit-GGUF # Run inference directly in the terminal: llama-cli -hf tencent/Hy-MT2-1.8B-2Bit-GGUF
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf tencent/Hy-MT2-1.8B-2Bit-GGUF # Run inference directly in the terminal: ./llama-cli -hf tencent/Hy-MT2-1.8B-2Bit-GGUF
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf tencent/Hy-MT2-1.8B-2Bit-GGUF # Run inference directly in the terminal: ./build/bin/llama-cli -hf tencent/Hy-MT2-1.8B-2Bit-GGUF
Use Docker
docker model run hf.co/tencent/Hy-MT2-1.8B-2Bit-GGUF
- LM Studio
- Jan
- Ollama
How to use tencent/Hy-MT2-1.8B-2Bit-GGUF with Ollama:
ollama run hf.co/tencent/Hy-MT2-1.8B-2Bit-GGUF
- Unsloth Studio new
How to use tencent/Hy-MT2-1.8B-2Bit-GGUF with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for tencent/Hy-MT2-1.8B-2Bit-GGUF to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for tencent/Hy-MT2-1.8B-2Bit-GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for tencent/Hy-MT2-1.8B-2Bit-GGUF to start chatting
- Docker Model Runner
How to use tencent/Hy-MT2-1.8B-2Bit-GGUF with Docker Model Runner:
docker model run hf.co/tencent/Hy-MT2-1.8B-2Bit-GGUF
- Lemonade
How to use tencent/Hy-MT2-1.8B-2Bit-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull tencent/Hy-MT2-1.8B-2Bit-GGUF
Run and chat with the model
lemonade run user.Hy-MT2-1.8B-2Bit-GGUF-{{QUANT_TAG}}List all available models
lemonade list
Jason commited on
Commit ·
d8566a4
1
Parent(s): 9367825
Update report links and citation
Browse files- HY_MT2_0_Report.pdf +0 -3
- README.md +10 -9
- README_CN.md +10 -9
HY_MT2_0_Report.pdf
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:618b3db032d236d5b3cf47847a639f57bf6cc57becd9321ef1a9ea7722b2e1bf
|
| 3 |
-
size 2326591
|
|
|
|
|
|
|
|
|
|
|
|
README.md
CHANGED
|
@@ -23,7 +23,8 @@ base_model:
|
|
| 23 |
<p align="center">
|
| 24 |
🖥️ <a href="https://aistudio.tencent.com/llm/en?tabIndex=0"><b>Official Website</b></a> |
|
| 25 |
💬 <a href="https://github.com/Tencent-Hunyuan/Hy-MT2"><b>GitHub</b></a> |
|
| 26 |
-
🪡 <a href="https://github.com/Tencent/AngelSlim/tree/main"><b>AngelSlim</b></a>
|
|
|
|
| 27 |
|
| 28 |
## Model Introduction
|
| 29 |
|
|
@@ -51,7 +52,7 @@ Now, Tencent Hy is officially partnering with WMT26 for the "Video Subtitle Tran
|
|
| 51 |
<img src="imgs/main_result.png" width = "100%" />
|
| 52 |
</div>
|
| 53 |
|
| 54 |
-
For more experimental results and analysis, please refer to our [report](
|
| 55 |
|
| 56 |
|
| 57 |
|
|
@@ -282,15 +283,15 @@ We provide [AngelSlim](https://github.com/tencent/AngelSlim), an easy-to-use, co
|
|
| 282 |
## Citing Hy-MT2
|
| 283 |
|
| 284 |
```bibtex
|
| 285 |
-
@misc{
|
| 286 |
-
title={
|
| 287 |
-
author={Mao Zheng and Zheng Li and Tao Chen and Mingyang Song and
|
| 288 |
-
year={
|
| 289 |
-
eprint={
|
| 290 |
archivePrefix={arXiv},
|
| 291 |
primaryClass={cs.CL},
|
| 292 |
-
url={https://arxiv.org/abs/
|
| 293 |
-
}
|
| 294 |
```
|
| 295 |
|
| 296 |
## Contact Us
|
|
|
|
| 23 |
<p align="center">
|
| 24 |
🖥️ <a href="https://aistudio.tencent.com/llm/en?tabIndex=0"><b>Official Website</b></a> |
|
| 25 |
💬 <a href="https://github.com/Tencent-Hunyuan/Hy-MT2"><b>GitHub</b></a> |
|
| 26 |
+
🪡 <a href="https://github.com/Tencent/AngelSlim/tree/main"><b>AngelSlim</b></a> |
|
| 27 |
+
📚 <a href="https://arxiv.org/pdf/2605.22064"><b>Hy-MT2 Report</b></a></p>
|
| 28 |
|
| 29 |
## Model Introduction
|
| 30 |
|
|
|
|
| 52 |
<img src="imgs/main_result.png" width = "100%" />
|
| 53 |
</div>
|
| 54 |
|
| 55 |
+
For more experimental results and analysis, please refer to our [report](https://arxiv.org/pdf/2605.22064).
|
| 56 |
|
| 57 |
|
| 58 |
|
|
|
|
| 283 |
## Citing Hy-MT2
|
| 284 |
|
| 285 |
```bibtex
|
| 286 |
+
@misc{zheng2026hymt2familyfastefficient,
|
| 287 |
+
title={Hy-MT2: A Family of Fast, Efficient and Powerful Multilingual Translation Models in the Wild},
|
| 288 |
+
author={Mao Zheng and Zheng Li and Tao Chen and Bo Lv and Mingrui Sun and Mingyang Song and Jinlong Song and Hong Huang and Decheng Wu and Hai Wang and Yifan Song and Yanfeng Chen and Guanwei Zhang},
|
| 289 |
+
year={2026},
|
| 290 |
+
eprint={2605.22064},
|
| 291 |
archivePrefix={arXiv},
|
| 292 |
primaryClass={cs.CL},
|
| 293 |
+
url={https://arxiv.org/abs/2605.22064},
|
| 294 |
+
}
|
| 295 |
```
|
| 296 |
|
| 297 |
## Contact Us
|
README_CN.md
CHANGED
|
@@ -19,7 +19,8 @@
|
|
| 19 |
<p align="center">
|
| 20 |
🖥️ <a href="https://aistudio.tencent.com/llm/zh?tabIndex=0"><b>官方网站</b></a> |
|
| 21 |
💬 <a href="https://github.com/Tencent-Hunyuan/Hy-MT2"><b>GitHub</b></a> |
|
| 22 |
-
🪡 <a href="https://github.com/Tencent/AngelSlim/tree/main"><b>AngelSlim</b></a>
|
|
|
|
| 23 |
|
| 24 |
|
| 25 |
## 模型介绍
|
|
@@ -46,7 +47,7 @@ Hy-MT2 是一款面向真实复杂场景的“快思考”多语言翻译模型
|
|
| 46 |
<img src="imgs/main_result.png" width = "100%" />
|
| 47 |
</div>
|
| 48 |
|
| 49 |
-
更多的实验效果和分析可以参考我们的[报告](
|
| 50 |
|
| 51 |
|
| 52 |
|
|
@@ -279,15 +280,15 @@ Hy-MT2提供了完整的模型训练流程,支持全量微调和 LoRA 微调
|
|
| 279 |
## Citing Hy-MT2
|
| 280 |
|
| 281 |
```bibtex
|
| 282 |
-
@misc{
|
| 283 |
-
title={
|
| 284 |
-
author={Mao Zheng and Zheng Li and Tao Chen and Mingyang Song and
|
| 285 |
-
year={
|
| 286 |
-
eprint={
|
| 287 |
archivePrefix={arXiv},
|
| 288 |
primaryClass={cs.CL},
|
| 289 |
-
url={https://arxiv.org/abs/
|
| 290 |
-
}
|
| 291 |
```
|
| 292 |
|
| 293 |
## 联系我们
|
|
|
|
| 19 |
<p align="center">
|
| 20 |
🖥️ <a href="https://aistudio.tencent.com/llm/zh?tabIndex=0"><b>官方网站</b></a> |
|
| 21 |
💬 <a href="https://github.com/Tencent-Hunyuan/Hy-MT2"><b>GitHub</b></a> |
|
| 22 |
+
🪡 <a href="https://github.com/Tencent/AngelSlim/tree/main"><b>AngelSlim</b></a> |
|
| 23 |
+
📚 <a href="https://arxiv.org/pdf/2605.22064"><b>Hy-MT2报告</b></a></p>
|
| 24 |
|
| 25 |
|
| 26 |
## 模型介绍
|
|
|
|
| 47 |
<img src="imgs/main_result.png" width = "100%" />
|
| 48 |
</div>
|
| 49 |
|
| 50 |
+
更多的实验效果和分析可以参考我们的[报告](https://arxiv.org/pdf/2605.22064)。
|
| 51 |
|
| 52 |
|
| 53 |
|
|
|
|
| 280 |
## Citing Hy-MT2
|
| 281 |
|
| 282 |
```bibtex
|
| 283 |
+
@misc{zheng2026hymt2familyfastefficient,
|
| 284 |
+
title={Hy-MT2: A Family of Fast, Efficient and Powerful Multilingual Translation Models in the Wild},
|
| 285 |
+
author={Mao Zheng and Zheng Li and Tao Chen and Bo Lv and Mingrui Sun and Mingyang Song and Jinlong Song and Hong Huang and Decheng Wu and Hai Wang and Yifan Song and Yanfeng Chen and Guanwei Zhang},
|
| 286 |
+
year={2026},
|
| 287 |
+
eprint={2605.22064},
|
| 288 |
archivePrefix={arXiv},
|
| 289 |
primaryClass={cs.CL},
|
| 290 |
+
url={https://arxiv.org/abs/2605.22064},
|
| 291 |
+
}
|
| 292 |
```
|
| 293 |
|
| 294 |
## 联系我们
|