voxmenthe's picture
394bcc7b8a1ac0af96cda777cd5244fa248d6c1f86e5e961db046ba4c089f485
541b23d verified
|
raw
history blame
683 Bytes
metadata
license: cc-by-nc-nd-3.0
tags:
  - mlx

mlx-community/SFR-Iterative-DPO-LLaMA-3-8B-R-unquantized

The Model mlx-community/SFR-Iterative-DPO-LLaMA-3-8B-R-unquantized 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("mlx-community/SFR-Iterative-DPO-LLaMA-3-8B-R-unquantized")
response = generate(model, tokenizer, prompt="hello", verbose=True)