Instructions to use MoYoYoTech/Translator with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use MoYoYoTech/Translator with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf MoYoYoTech/Translator:Q5_0
# Run inference directly in the terminal:
llama cli -hf MoYoYoTech/Translator:Q5_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf MoYoYoTech/Translator:Q5_0
# Run inference directly in the terminal:
llama cli -hf MoYoYoTech/Translator:Q5_0

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 MoYoYoTech/Translator:Q5_0
# Run inference directly in the terminal:
./llama-cli -hf MoYoYoTech/Translator:Q5_0

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 MoYoYoTech/Translator:Q5_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf MoYoYoTech/Translator:Q5_0

Use Docker

docker model run hf.co/MoYoYoTech/Translator:Q5_0

LM Studio
Jan
Ollama
How to use MoYoYoTech/Translator with Ollama:
```
ollama run hf.co/MoYoYoTech/Translator:Q5_0
```
Unsloth Desktop

How to use MoYoYoTech/Translator with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf MoYoYoTech/Translator:Q5_0

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "MoYoYoTech/Translator:Q5_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use MoYoYoTech/Translator with Docker Model Runner:
```
docker model run hf.co/MoYoYoTech/Translator:Q5_0
```

Lemonade

How to use MoYoYoTech/Translator with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull MoYoYoTech/Translator:Q5_0

Run and chat with the model

lemonade run user.Translator-Q5_0

List all available models

lemonade list

Hermes Agent

How to use MoYoYoTech/Translator with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf MoYoYoTech/Translator:Q5_0

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default MoYoYoTech/Translator:Q5_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use MoYoYoTech/Translator with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf MoYoYoTech/Translator:Q5_0

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "MoYoYoTech/Translator:Q5_0" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Translator

Commit History

May 14, 2025

08:16
[fix]: readme

Xin Zhang

5d2fc61
08:10
[feature]: add frontend src.

Xin Zhang

b1cc7ae

May 12, 2025

07:53
remove some mixture of hotwords json

daihui.zhang

5873ede

Apr 30, 2025

09:40
Merge branch 'vad'⁠

Xin Zhang

960176b
09:30
[fix]: readme.

Xin Zhang

6a47ad7
09:28
[fix]: add.

Xin Zhang

a4e7603
08:10
[feature]: remove experimental models.

Xin Zhang

27c43dd
07:56
[fix]: web bugfix.

Xin Zhang

b11033f
01:55
update prompt for en

yujuanqin

9e942a1
01:41
[feature]: add session history.

Xin Zhang

becec65

Apr 29, 2025

09:08
Merge branch 'vad' of https://huggingface.co/MoYoYoTech/Translator into vad

yujuanqin

939d178
09:07
restore min_silence_duration_ms to 100

yujuanqin

c3d327a
08:14
add hotwords config to mapping

daihui.zhang

e7b7ca4
08:11
add hotwords

yujuanqin

9dbbf4e
07:12
add hotwords config to mapping

daihui.zhang

608a602
06:36
add hotwords

yujuanqin

9b63460
03:58
update vad threshold

yujuanqin

91c839e
03:55
remove english words, add more Chinese hotwords

yujuanqin

84f4629
02:09
rename processing pipe

daihui.zhang

cb2f705
01:59
rename filenames

daihui.zhang

9494251

Apr 28, 2025

15:09
Merge branch 'vad'⁠

Xin Zhang

b8873f5
09:45
add words ignore

daihui.zhang

0a6c788
06:58
update vad min_silence_duration_ms to 100

yujuanqin

6485991
06:55
update prompt for en

yujuanqin

de24d4c
06:37
update prompt for en

yujuanqin

92c088c
03:52
fix bug of queue lock

daihui.zhang

9694503
02:09
Merge branch 'vad'⁠

Xin Zhang

9365e6a
02:06
update english prompt

daihui.zhang

22453ce
01:56
[fix]: upate web.

Xin Zhang

58fbad4
01:55
[fix]: web.

Xin Zhang

e3764f1
01:44
Merge branch 'vad'⁠

Xin Zhang

31225c2
01:39
remove truncate in audio buffer

daihui.zhang

812e042
01:39
Merge branch 'vad'⁠

Xin Zhang

95624f1
01:38
[docs]: update installation.

Xin Zhang

9435daa
01:32
Merge branch 'vad'⁠

Xin Zhang

75127fb
01:31
[fix]: remove 3b

Xin Zhang

fef15f0
01:23
Merge branch 'vad'⁠

Xin Zhang

eb39b90

Apr 27, 2025

14:51
[fix]: update web.

Xin Zhang

9226b1d
14:48
[fix]: whisper_full_with_state: input is too short - 990 ms < 1000 ms. consider padding the input audio with silence.

Xin Zhang

1b8024b
14:03
[fix]: to 1.5b

Xin Zhang

632b469
09:38
filter empty message

daihui.zhang

0b2caa6
08:40
update zh-en prompt add limit

daihui.zhang

d138458
07:34
update code structures and some code

daihui.zhang

83ea845
07:07
update prompts and words

daihui.zhang

b37f1c3

Apr 25, 2025

13:56
[fix]: config.

Xin Zhang

7858456
13:27
Merge branch 'vad'⁠

Xin Zhang

0a1db62
08:58
Merge branch 'vad' of https://huggingface.co/MoYoYoTech/Translator into vad

yujuanqin

ad6ae02
08:56
update llm prompt

moyoyo

bfd9052
08:40
update whipser model default

daihui.zhang

d2c2833
08:18
update whipser model

daihui.zhang

1bc8991

Commit History

May 14, 2025

[fix]: readme

[feature]: add frontend src.

May 12, 2025

remove some mixture of hotwords json

Apr 30, 2025

Merge branch 'vad'⁠

[fix]: readme.

[fix]: add.

[feature]: remove experimental models.

[fix]: web bugfix.

update prompt for en

[feature]: add session history.

Apr 29, 2025

Merge branch 'vad' of https://huggingface.co/MoYoYoTech/Translator into vad

restore min_silence_duration_ms to 100

add hotwords config to mapping

add hotwords

add hotwords config to mapping

add hotwords

update vad threshold

remove english words, add more Chinese hotwords

rename processing pipe

rename filenames

Apr 28, 2025

Merge branch 'vad'⁠

add words ignore

update vad min_silence_duration_ms to 100

update prompt for en

update prompt for en

fix bug of queue lock

Merge branch 'vad'⁠

update english prompt

[fix]: upate web.

[fix]: web.

Merge branch 'vad'⁠

remove truncate in audio buffer

Merge branch 'vad'⁠

[docs]: update installation.

Merge branch 'vad'⁠

[fix]: remove 3b

Merge branch 'vad'⁠

Apr 27, 2025

[fix]: update web.

[fix]: whisper_full_with_state: input is too short - 990 ms < 1000 ms. consider padding the input audio with silence.

[fix]: to 1.5b

filter empty message

update zh-en prompt add limit

update code structures and some code

update prompts and words

Apr 25, 2025

[fix]: config.

Merge branch 'vad'⁠

Merge branch 'vad' of https://huggingface.co/MoYoYoTech/Translator into vad

update llm prompt

update whipser model default

update whipser model