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

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

Update README_CN.md

by woodchen7 - opened 2 days ago

base: refs/heads/main

←

from: refs/pr/3

Discussion Files changed

-1

Files changed (1) hide show

README_CN.md +2 -1

README_CN.md CHANGED Viewed

@@ -24,6 +24,7 @@
 ## 模型介绍
 Hy-MT2 是一款面向真实复杂场景的“快思考”多语言翻译模型家族，涵盖 1.8B、7B 和 30B-A3B（MoE）三种体量，支持 33 种语言互译并具备强大的多语言指令遵循能力。在端侧部署上，得益于 AngelSlim 1.25-bit 极端量化，其 1.8B 模型仅需 440MB 存储空间，推理速度显著提升 1.5 倍。多维度评测表明，Hy-MT2 在通用、真实业务、专业领域及指令遵循等翻译任务中表现卓越：7B 和 30B-A3B 模型性能不仅超越了 DeepSeek-V4-Pro、Kimi K2.6 等开源模型在快思考模式下的表现，轻量级 1.8B 模型亦在整体上超越了微软和豆包等主流商业 API。
@@ -155,7 +156,7 @@ python3 -m sglang.launch_server --model tencent/Hy-MT2-30B-A3B --tp 1
 ### llama_cpp
-**❕❕ This gguf depends on our STQ kernel, which is released at [PR #22836](https://github.com/ggml-org/llama.cpp/pull/22836).**
 #### Clone llama.cpp

 ## 模型介绍
+Hy-MT2-1.8B-2Bit-GGUF由AngelSlim产出，更多技术细节可以参考 [[AngelSlim]](https://github.com/Tencent/AngelSlim)。
 Hy-MT2 是一款面向真实复杂场景的“快思考”多语言翻译模型家族，涵盖 1.8B、7B 和 30B-A3B（MoE）三种体量，支持 33 种语言互译并具备强大的多语言指令遵循能力。在端侧部署上，得益于 AngelSlim 1.25-bit 极端量化，其 1.8B 模型仅需 440MB 存储空间，推理速度显著提升 1.5 倍。多维度评测表明，Hy-MT2 在通用、真实业务、专业领域及指令遵循等翻译任务中表现卓越：7B 和 30B-A3B 模型性能不仅超越了 DeepSeek-V4-Pro、Kimi K2.6 等开源模型在快思考模式下的表现，轻量级 1.8B 模型亦在整体上超越了微软和豆包等主流商业 API。
 ### llama_cpp
+**❕❕ This gguf depends on our STQ kernel, which is released at [PR #19357](https://github.com/ggml-org/llama.cpp/pull/19357).**
 #### Clone llama.cpp