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
| 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](https://huggingface.co/typealias/SFR-Iterative-DPO-Llama-3-8B-R-mx-4bit) was converted to MLX format from [Salesforce/SFR-Iterative-DPO-LLaMA-3-8B-R](https://huggingface.co/Salesforce/SFR-Iterative-DPO-LLaMA-3-8B-R) using mlx-lm version **0.13.0**. | |
| ## Use with mlx | |
| ```bash | |
| pip install mlx-lm | |
| ``` | |
| ```python | |
| 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) | |
| ``` | |