Downloads · 30 days
135
21% of all-time downloads
gpt-oss-120b-abliterated
joshebbs/gpt-oss-120b-abliterated
gpt-oss-120b-abliterated is a machine learning model from joshebbs. 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.
Abliterated version of openai/gpt-oss-120b with refusal directions removed from layers 13-25.
All-time downloads
649
Public
Parameters
120B
65.3 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors65.2 GB · 100%
Parameter types
How the weights are stored.
U8118B · 98%
Base models
Model card
From the Hugging Face model README
GPT-OSS 120B Abliterated
Abliterated version of openai/gpt-oss-120b with refusal directions removed from layers 13-25.
What is Abliteration?
Abliteration removes the refusal direction from model weights using norm-preserving biprojected abliteration. This allows the model to respond to all prompts without explicit refusal, while preserving model quality. See the abliteration blog post for details.
Model Details
- Base Model: openai/gpt-oss-120b (Apache 2.0)
- Architecture: MoE, 120B total params, 5.1B active per token
- Format: Safetensors (original precision)
- Abliterated Layers: 13-25 (refusal direction removed)
- Method: jim-plus/llm-abliteration with projected measurement
Usage
Works as a drop-in replacement for gpt-oss-120b with any compatible serving framework (vLLM, SGLang, etc.).
vllm serve joshebbs/gpt-oss-120b-abliterated --quantization mxfp4
Hardware
Tested on 2x NVIDIA DGX Spark (GB10) with TP=2 achieving 57-59 tok/s decode with MXFP4 quantization.
- Type
- gpt_oss
- License
- apache-2.0
- Created
- Apr 24, 2026
- Updated
- Apr 25, 2026