|
Download README.md from YanLabs/Seed-OSS-36B-Instruct-MPOA: direct link, hf CLI and curl.
- Browser
- Download file 2.38 kB
-
https://huggingface.co/YanLabs/Seed-OSS-36B-Instruct-MPOA/resolve/main/README.md
- Command line
-
hf download hf://YanLabs/Seed-OSS-36B-Instruct-MPOA/README.md
-
curl -L -o README.md https://huggingface.co/YanLabs/Seed-OSS-36B-Instruct-MPOA/resolve/main/README.md
2.38 kB
| license: apache-2.0 | |
| base_model: | |
| - ByteDance-Seed/Seed-OSS-36B-Instruct | |
| pipeline_tag: text-generation | |
| # YanLabs/Seed-OSS-36B-Instruct-MPOA | |
| This is an abliterated version of [ByteDance-Seed/Seed-OSS-36B-Instruct](https://huggingface.co/ByteDance-Seed/Seed-OSS-36B-Instruct) using the norm-preserving biprojected abliteration technique. | |
| **⚠️ Warning**: Safety guardrails and refusal mechanisms have been removed through abliteration. This model may generate harmful content and is intended for mechanistic interpretability research only. | |
| ## Model Details | |
| ### Model Description | |
| This model applies **norm-preserving biprojected abliteration** to remove refusal behaviors while preserving the model's original capabilities. The technique surgically removes "refusal directions" from the model's activation space without traditional fine-tuning. | |
| - **Developed by**: YanLabs | |
| - **Model type**: Causal Language Model (Transformer) | |
| - **License**: apache-2.0 | |
| - **Base model**: [ByteDance-Seed/Seed-OSS-36B-Instruct](https://huggingface.co/ByteDance-Seed/Seed-OSS-36B-Instruct) | |
| ### Model Sources | |
| - **Base Model**: [ByteDance-Seed/Seed-OSS-36B-Instruct](https://huggingface.co/ByteDance-Seed/Seed-OSS-36B-Instruct) | |
| - **Abliteration Tool**: [jim-plus/llm-abliteration](https://github.com/jim-plus/llm-abliteration) | |
| - **Paper**: [Norm-Preserving Biprojected Abliteration](https://huggingface.co/blog/grimjim/norm-preserving-biprojected-abliteration) | |
| ## Uses | |
| ### Intended Use | |
| - **Research**: Mechanistic interpretability studies | |
| - **Analysis**: Understanding LLM safety mechanisms | |
| - **Development**: Testing abliteration techniques | |
| ### Out-of-Scope Use | |
| - ❌ Production deployments | |
| - ❌ User-facing applications | |
| - ❌ Generating harmful content for malicious purposes | |
| ## Limitations | |
| - Abliteration does not guarantee complete removal of all refusals | |
| - May generate unsafe or harmful content | |
| - Model behavior may be unpredictable in edge cases | |
| - No explicit harm prevention mechanisms remain | |
| ## Citation | |
| If you use this model in your research, please cite: | |
| ```bibtex | |
| @misc{Seed-OSS-36B-Instruct-MPOA, | |
| author = {YanLabs}, | |
| title = {Seed-OSS-36B-Instruct-MPOA}, | |
| year = {2025}, | |
| publisher = {HuggingFace}, | |
| howpublished = {\url{https://huggingface.co/YanLabs/Seed-OSS-36B-Instruct-MPOA}}, | |
| note = {Abliterated using norm-preserving biprojected technique} | |
| } |