Downloads · 30 days
10
18% of all-time downloads
GRM-Kerlin-3b-Abliterated
usermma/GRM-Kerlin-3b-Abliterated
GRM-Kerlin-3b-Abliterated is a machine learning model from usermma. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This model was abliterated using the heretic method via OBLITERATUS.
All-time downloads
56
Public
Parameters
3.1B
6.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors6.2 GB · 100%
At a glance
- Model type
- qwen2
- Access
- Public
- Created
- Jul 10, 2026
- Updated
- Jul 10, 2026
- SHA
- 10b92b38
Base models
Model card
From the Hugging Face model README
GRM-Kerlin-3b-OBLITERATED
This model was abliterated using the heretic method via
OBLITERATUS.
| Detail | Value |
|---|---|
| Base model | OrionLLM/GRM-Kerlin-3b |
| Method | heretic |
| Source | obliterate |
How to Use
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("GRM-Kerlin-3b-OBLITERATED")
tokenizer = AutoTokenizer.from_pretrained("GRM-Kerlin-3b-OBLITERATED")
prompt = "Hello, how are you?"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
About OBLITERATUS
OBLITERATUS is an open-source tool for removing refusal behavior from language models via activation engineering (abliteration). Learn more at github.com/elder-plinius/OBLITERATUS.
- Type
- qwen2
- Languages
- en
- Created
- Jul 10, 2026
- Updated
- Jul 10, 2026