MLX
llama
Edit model card

mlx-community/bagel-dpo-34b-v0.2-4bit-mlx

This model was converted to MLX format from jondurbin/bagel-dpo-34b-v0.2. Refer to the original model card for more details on the model.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/bagel-dpo-34b-v0.2-4bit-mlx")
response = generate(model, tokenizer, prompt="hello", verbose=True)
Downloads last month
0
Unable to determine this model’s pipeline type. Check the docs .

Datasets used to train mlx-community/bagel-dpo-34b-v0.2-4bit-mlx