Instructions to use m-i/HY-MT1.5-7B-mlx-5Bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use m-i/HY-MT1.5-7B-mlx-5Bit with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("translation", model="m-i/HY-MT1.5-7B-mlx-5Bit")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("m-i/HY-MT1.5-7B-mlx-5Bit") model = AutoModelForCausalLM.from_pretrained("m-i/HY-MT1.5-7B-mlx-5Bit") - MLX
How to use m-i/HY-MT1.5-7B-mlx-5Bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir HY-MT1.5-7B-mlx-5Bit m-i/HY-MT1.5-7B-mlx-5Bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
m-i/HY-MT1.5-7B-mlx-5Bit
The Model m-i/HY-MT1.5-7B-mlx-5Bit was converted to MLX format from tencent/HY-MT1.5-7B using mlx-lm version 0.28.3.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("m-i/HY-MT1.5-7B-mlx-5Bit")
prompt="hello"
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
- 16
Model size
1B params
Tensor type
BF16
Β·
U32 Β·
Hardware compatibility
Log In to add your hardware
5-bit
Model tree for m-i/HY-MT1.5-7B-mlx-5Bit
Base model
tencent/HY-MT1.5-7B