metadata

language:
  - nl
license: apache-2.0
tags:
  - generated_from_trainer
  - GEITje
  - mlx
datasets:
  - Rijgersberg/no_robots_nl
  - Rijgersberg/ultrachat_10k_nl
  - BramVanroy/dutch_chat_datasets
base_model: Rijgersberg/GEITje-7B
pipeline_tag: conversational
model-index:
  - name: GEITje-7B-chat-v2
    results: []

Rijgersberg/GEITje-7B-chat-v2-mlx

This model was converted to MLX format from Rijgersberg/GEITje-7B-chat-v2. 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-chat-v2-mlx")
response = generate(model, tokenizer, prompt="hello", verbose=True)