Modelpublic

FritzStack/IRF-QWEN4B-mlx-Q4

sourceHugging Faceapache-2.0updated 7mo agoView on Hugging Face

0likes67downloads

Model Card

FritzStack/IRF-Qwen4B4bit-merged_2epo-mlx-4Bit

The Model FritzStack/IRF-Qwen_4B_4bit-merged_2epo-mlx-4Bit was converted to MLX format from FritzStack/IRF-Qwen_4B_4bit-merged_2epo using mlx-lm version 0.29.1.

Use with mlx

bash

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

python

from TONY.IRF import IRFPredictor_mlx

text = 'Some days I keep living, even though I feel completely alone in the world'
irf = IRFPredictor_mlx(model_name='FritzStack/IRF-QWEN4B-mlx-Q4')
irf.highlight_evidence_IRF(text)