Downloads · 30 days
19
5% of all-time downloads
gpt-oss-20b_colab-heretic
nek0o/gpt-oss-20b_colab-heretic
gpt-oss-20b_colab-heretic is a machine learning model from nek0o. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
422
Public
Parameters
20.9B
41.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors41.8 GB · 100%
At a glance
- Model type
- gpt_oss
- Access
- Public
- Created
- Nov 19, 2025
- Updated
- Nov 19, 2025
- SHA
- 4e082451
Model card
From the Hugging Face model README
This is a decensored version of nek0o/gpt-oss-20b_colab, made using Heretic v1.0.1
Abliteration parameters
| Parameter | Value |
|---|---|
| direction_index | 12.81 |
| attn.o_proj.max_weight | 1.34 |
| attn.o_proj.max_weight_position | 14.23 |
| attn.o_proj.min_weight | 1.19 |
| attn.o_proj.min_weight_distance | 3.21 |
| mlp.down_proj.max_weight | 1.49 |
| mlp.down_proj.max_weight_position | 15.07 |
| mlp.down_proj.min_weight | 1.46 |
| mlp.down_proj.min_weight_distance | 11.84 |
Performance
| Metric | This model | Original model (nek0o/gpt-oss-20b_colab) |
|---|---|---|
| KL divergence | 0.00 | 0 (by definition) |
| Refusals | 93/100 | 96/100 |
gpt-oss-20b_colab - GGUF
This model was finetuned and converted to GGUF format using Unsloth.
Example usage:
- For text only LLMs: llama-cli --hf repo_id/model_name -p "why is the sky blue?"
- For multimodal models: llama-mtmd-cli -m model_name.gguf --mmproj mmproj_file.gguf
Available Model files:
gpt-oss-20b.MXFP4.gguf
Ollama
An Ollama Modelfile is included for easy deployment.
- Type
- gpt_oss
- Created
- Nov 19, 2025
- Updated
- Nov 19, 2025