Downloads · 30 days
13
9% of all-time downloads
EOPSA-Qwen3-4B
neuqrui/EOPSA-Qwen3-4B
EOPSA-Qwen3-4B is a text generation model from neuqrui. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
EOPSA (Efficient On-Policy Self-Distilled Safety Alignment) checkpoint of Qwen3-4B.
All-time downloads
142
Public
Parameters
4.4B
8.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors8.8 GB · 100%
At a glance
- Task
- Text Generation
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- Aug 8, 2026
- Updated
- Sep 26, 2026
- SHA
- ea7664ee
Try a prompt
Base models
Model card
From the Hugging Face model README
EOPSA-Qwen3-4B
EOPSA (Efficient On-Policy Self-Distilled Safety Alignment) checkpoint of Qwen3-4B.
- Training code: https://github.com/neuqrui/EOPSA
- Model collection: https://huggingface.co/collections/neuqrui/eopsa
- Safety evaluation: https://github.com/neuqrui/LLM-Safety-Eval
Load
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "neuqrui/EOPSA-Qwen3-4B"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype="auto",
device_map="auto",
)
- Task
- Text Generation
- Type
- qwen3
- License
- apache-2.0
- Created
- Aug 8, 2026
- Updated
- Sep 26, 2026