HuggingFaceH4/ultrachat_200k
Viewer • Updated • 515k • 88.6k • 875
How to use voxmenthe/stablelm-2-12b-chat-mlx-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir stablelm-2-12b-chat-mlx-4bit voxmenthe/stablelm-2-12b-chat-mlx-4bit
This model was converted to MLX format from stabilityai/stablelm-2-12b-chat using mlx-lm version 0.8.0.
Refer to the original model card for more details on the model.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("voxmenthe/stablelm-2-12b-chat-mlx-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
Quantized