Instructions to use mlx-community/HY-MT1.5-1.8B-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/HY-MT1.5-1.8B-4bit with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm
# if on a CUDA device, also pip install mlx[cuda]

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/HY-MT1.5-1.8B-4bit")

prompt = "Once upon a time in"
text = generate(model, tokenizer, prompt=prompt, verbose=True)

Transformers

How to use mlx-community/HY-MT1.5-1.8B-4bit with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="mlx-community/HY-MT1.5-1.8B-4bit")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mlx-community/HY-MT1.5-1.8B-4bit", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

vLLM

How to use mlx-community/HY-MT1.5-1.8B-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mlx-community/HY-MT1.5-1.8B-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlx-community/HY-MT1.5-1.8B-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mlx-community/HY-MT1.5-1.8B-4bit

SGLang

How to use mlx-community/HY-MT1.5-1.8B-4bit with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "mlx-community/HY-MT1.5-1.8B-4bit" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlx-community/HY-MT1.5-1.8B-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "mlx-community/HY-MT1.5-1.8B-4bit" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlx-community/HY-MT1.5-1.8B-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

MLX LM

How to use mlx-community/HY-MT1.5-1.8B-4bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Generate some text
mlx_lm.generate --model "mlx-community/HY-MT1.5-1.8B-4bit" --prompt "Once upon a time"

Docker Model Runner
How to use mlx-community/HY-MT1.5-1.8B-4bit with Docker Model Runner:
```
docker model run hf.co/mlx-community/HY-MT1.5-1.8B-4bit
```

mlx-community/HY-MT1.5-1.8B-4bit

The Model mlx-community/HY-MT1.5-1.8B-4bit was converted to MLX format from tencent/HY-MT1.5-1.8B using mlx-lm version 0.29.1.

You can find other similar translation-related MLX model quants for an Apple Mac at https://huggingface.co/bibproj

The following parameters values are recommended for inference:

top_k: 20
top_p: 0.6
repetition_penalty: 1.05
temperature: 0.7

36 Supported Languages: Chinese, English, French, Portuguese, Spanish, Japanese, Turkish, Russian, Korean, Thai, Italian, German, Vietnamese, Malay, Indonesian, Filipino, Hindi, Traditional Chinese, Polish, Czech, Dutch, Khmer, Burmese, Persian, Gujarati, Urdu, Telugu, Marathi, Hebrew, Bengali, Tamil, Ukrainian, Tibetan, Kazakh, Mongolian, Uyghur, and Cantonese.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/HY-MT1.5-1.8B-4bit")

prompt="Translate from English to French: Hi there!"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)

Downloads last month: 385

Safetensors

Model size

0.3B params

Tensor type

BF16

U32

MLX

Hardware compatibility

Quantized

Model tree for mlx-community/HY-MT1.5-1.8B-4bit

Base model

tencent/HY-MT1.5-1.8B

Finetuned

(43)

this model