Instructions to use mlx-community/Yi-1.5-9B-Chat-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/Yi-1.5-9B-Chat-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download mlx-community/Yi-1.5-9B-Chat-4bit --local-dir Yi-1.5-9B-Chat-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
|
Download README.md from mlx-community/Yi-1.5-9B-Chat-4bit: direct link, hf CLI and curl.
- Browser
- Download file 612 Bytes
-
https://huggingface.co/mlx-community/Yi-1.5-9B-Chat-4bit/resolve/main/README.md
- Command line
-
hf download hf://mlx-community/Yi-1.5-9B-Chat-4bit/README.md
-
curl -L -o README.md https://huggingface.co/mlx-community/Yi-1.5-9B-Chat-4bit/resolve/main/README.md
612 Bytes
metadata
license: apache-2.0
tags:
- mlx
mlx-community/Yi-1.5-9B-Chat-4bit
The Model mlx-community/Yi-1.5-9B-Chat-4bit was converted to MLX format from 01-ai/Yi-1.5-9B-Chat using mlx-lm version 0.13.0.
Model added by Prince Canuma.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/Yi-1.5-9B-Chat-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)