FritzStack/HiTOP-Llama-3.2-3B_4bit-merged-mlx-4Bit

The Model FritzStack/HiTOP-Llama-3.2-3B_4bit-merged-mlx-4Bit was converted to MLX format from FritzStack/HiTOP-Llama-3.2-3B_4bit-merged using mlx-lm version 0.29.1.

Use with mlx

pip install mlx-lm
!pip install git+https://github.com/Fede-stack/TONYpy.git

from TONY.HiTOP import HiTOPPredictor_mlx
text = 'Some days I keep living, even though I feel completely alone in the world'
hitop = HiTOP_Predictor_mlx(model_name='FritzStack/HiTOP-Llama-3B-mlx-Q4')
hitop.predict_HiTOP(text)

Downloads last month: 65

Safetensors

Model size

0.5B params

Tensor type

BF16

U32

MLX

Hardware compatibility

4-bit

Model tree for FritzStack/HiTOP-Llama-3B-mlx-Q4

Base model

FritzStack/HiTOP-Llama-3B_4bit

Quantized

(1)

this model