salenew0rld/THaLLE-4bit-MLX

The Model salenew0rld/THaLLE-4bit-MLX was converted to MLX format from KBTG-Labs/THaLLE-0.1-7B-fa using mlx-lm version 0.14.2.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("salenew0rld/THaLLE-4bit-MLX")
response = generate(model, tokenizer, prompt="hello", verbose=True)

Downloads last month: 0

Safetensors

Model size

1.19B params

Tensor type

FP16

U32