mlx-community/Megac4ai-command-r-plus-4bit
This model was converted to MLX format from nitky/Megac4ai-command-r-plus using mlx-lm version 0.12.0.
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/Megac4ai-command-r-plus-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
- Downloads last month
- 27
Model size
25B params
Tensor type
F16
·
U32 ·
Hardware compatibility
Log In to add your hardware
Quantized
Model tree for mlx-community/Megac4ai-command-r-plus-4bit
Base model
CohereLabs/c4ai-command-r-plus