Instructions to use typealias/SFR-Iterative-DPO-Llama-3-8B-R-mx-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use typealias/SFR-Iterative-DPO-Llama-3-8B-R-mx-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir SFR-Iterative-DPO-Llama-3-8B-R-mx-4bit typealias/SFR-Iterative-DPO-Llama-3-8B-R-mx-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
metadata
license: cc-by-nc-nd-3.0
tags:
- mlx
typealias/SFR-Iterative-DPO-Llama-3-8B-R-mx-4bit
The Model typealias/SFR-Iterative-DPO-Llama-3-8B-R-mx-4bit was converted to MLX format from Salesforce/SFR-Iterative-DPO-LLaMA-3-8B-R using mlx-lm version 0.13.0.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("typealias/SFR-Iterative-DPO-Llama-3-8B-R-mx-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)