Downloads · 30 days
753
11% of all-time downloads
Qwen3-4B-Instruct-2507-uncensored-unslop-v2
electroglyph/Qwen3-4B-Instruct-2507-uncensored-unslop-v2
Qwen3-4B-Instruct-2507-uncensored-unslop-v2 is a text generation model from electroglyph. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
This is a GRPO finetune to remove slop from this model: Qwen3-4B-Instruct-2507-uncensored
All-time downloads
6.7K
Public
Parameters
4B
10.6 GB on disk
Likes
7
Public
Repo makeup
Click a slice to open those files.
.safetensors8 GB · 76%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- Nov 13, 2025
- Updated
- Nov 13, 2025
- SHA
- db150030
Try a prompt
Model card
From the Hugging Face model README
This is a GRPO finetune to remove slop from this model: Qwen3-4B-Instruct-2507-uncensored
It's not perfect, there are some before and after examples below.
I used the same method (mostly) as this model: gemma-3-4b-it-unslop-GRPO-v3
Note: This is not an RP tune, it's a compliant model with a different style from regular Qwen3 4B 2507.
My uncensoring dataset was generated by Gemma 3 27B abliterated model, which added a lot of Gemma writing style to this model.
It also added some Gemma style slop, which this finetune has helped mitigate.
I've uploaded a UD-Q4_K_XL GGUF with settings that I grabbed from Unsloth's quant using my lil utility: quant_clone
Here are some pics of before and after output with the slop highlighted and total at the bottom:
Prompt = "write a short story about a gothic romance, it should be around 500 words long"
Before:
After:
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3
- License
- apache-2.0
- Created
- Nov 13, 2025
- Updated
- Nov 13, 2025