Edit model card

voxmenthe/Smaug-Llama-3-70B-Instruct-mlx-8bit

The Model voxmenthe/Smaug-Llama-3-70B-Instruct-mlx-8bit was converted to MLX format from abacusai/Smaug-Llama-3-70B-Instruct using mlx-lm version 0.13.1.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("voxmenthe/Smaug-Llama-3-70B-Instruct-mlx-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
Downloads last month
2
Safetensors
Model size
19.8B params
Tensor type
FP16
·
U32
·

Datasets used to train voxmenthe/Smaug-Llama-3-70B-Instruct-mlx-8bit