Downloads · 30 days
9
13% of all-time downloads
Qwen3-4B-abliterated-v2
nitrox/Qwen3-4B-abliterated-v2
Qwen3-4B-abliterated-v2 is a machine learning model from nitrox. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This is an abliterated version of INC4AI/MiniMax-M2.5-int4-mixed-AutoRound.
All-time downloads
70
Public
Parameters
4B
16.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors8 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- Feb 20, 2026
- Updated
- Feb 20, 2026
- SHA
- 9b825ff5
Base models
Model card
From the Hugging Face model README
MiniMax-M2.5 Abliterated (int4)
This is an abliterated version of INC4AI/MiniMax-M2.5-int4-mixed-AutoRound.
Abliteration
Abliteration was performed using heretic — a multi-objective optimization framework that uses Optuna TPE to find the best LoRA-based abliteration parameters.
- Method: Heretic v1.2.0, LoRA + Optuna multi-objective optimization
- Base model: INC4AI/MiniMax-M2.5-int4-mixed-AutoRound (230B MoE)
- Format: int4 AutoRound (Marlin backend)
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained(
"nitrox/Qwen3-4B-abliterated-v2",
device_map="auto",
trust_remote_code=True,
)
tokenizer = AutoTokenizer.from_pretrained("nitrox/Qwen3-4B-abliterated-v2", trust_remote_code=True)
Disclaimer
This model has had its refusal mechanisms removed. Use responsibly.
- Type
- qwen3
- License
- apache-2.0
- Created
- Feb 20, 2026
- Updated
- Feb 20, 2026