pepsisoonji/pepsiLoRA
The Model pepsisoonji/pepsiLoRA was converted to MLX format from beomi/Llama-3-Open-Ko-8B using mlx-lm version 0.14.3.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("pepsisoonji/pepsiLoRA")
response = generate(model, tokenizer, prompt="hello", verbose=True)
- Downloads last month
- 1
Model size
1B params
Tensor type
F16
·
U32
·
Hardware compatibility
Log In
to add your hardware
Quantized