obvr/Llama-3-Lluca-8B
The Model obvr/Llama-3-Lluca-8B was converted to MLX format from NousResearch/Meta-Llama-3-8B-Instruct using mlx-lm version 0.13.0.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("obvr/Llama-3-Lluca-8B")
response = generate(model, tokenizer, prompt="hello", verbose=True)
- Downloads last month
- 6
Model size
8B params
Tensor type
BF16
·
Hardware compatibility
Log In to add your hardware
Quantized