Edit model card

mlx-community/aya-23-8B-8bit

The Model mlx-community/aya-23-8B-8bit was converted to MLX format from CohereForAI/aya-23-8B using mlx-lm version 0.13.1.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/aya-23-8B-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
Downloads last month
114
Safetensors
Model size
2.26B params
Tensor type
FP16
·
U32
·