metadata
language:
- nl
license: cc-by-nc-4.0
tags:
- alignment-handbook
- generated_from_trainer
- trl
- dpo
- geitje
- mlx
datasets:
- BramVanroy/ultra_feedback_dutch
base_model: BramVanroy/GEITje-7B-ultra-sft
pipeline_tag: conversational
model-index:
- name: BramVanroy/GEITje-7B-ultra
results: []
Rijgersberg/GEITje-7B-ultra-mlx
This model was converted to MLX format from BramVanroy/GEITje-7B-ultra
.
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("Rijgersberg/GEITje-7B-ultra-mlx")
response = generate(model, tokenizer, prompt="hello", verbose=True)