LLM EXPLORER 59,420 MODELS INDEXED

Unholy 8B DPO OAS by Undi95

By Undi95 · 19 downloads
HF Repo ↗ Copy URL

Unholy 8B DPO OAS is an open-source language model by Undi95. Features: 8b LLM, VRAM: 32.1GB, Context: 8K, LLM Explorer Score: 0.12.

  Conversational   Endpoints compatible   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Undi95/Unholy-8B-DPO-OAS 

Unholy 8B DPO OAS Parameters and Internals

Additional Notes 
The training uses a custom script for Orthogonal Activation Steering as a last step.
Training Details 
Methodology:
Orthogonal Activation Steering (OAS), followed by training 2 epochs of DPO on a toxic dataset
LLM NameUnholy 8B DPO OAS
Repository 🤗https://huggingface.co/Undi95/Unholy-8B-DPO-OAS 
Model Size8b
Required VRAM32.1 GB
Updated2026-07-14
MaintainerUndi95
Model Typellama
Model Files  4.9 GB: 1-of-7   4.8 GB: 2-of-7   5.0 GB: 3-of-7   5.0 GB: 4-of-7   4.8 GB: 5-of-7   5.0 GB: 6-of-7   2.6 GB: 7-of-7
Model ArchitectureLlamaForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.40.1
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|end_of_text|>
Vocabulary Size128256
Torch Data Typefloat32

Best Alternatives to Unholy 8B DPO OAS

Best Alternatives
Context / RAM
Downloads
Likes
...otron 8B UltraLong 4M Instruct4192K / 32.1 GB1135125
UltraLong Thinking4192K / 16.1 GB23
...a 3.1 8B UltraLong 4M Instruct4192K / 32.1 GB17624
...a 3.1 8B UltraLong 2M Instruct2096K / 32.1 GB8759
...otron 8B UltraLong 2M Instruct2096K / 32.1 GB12418
Cthulhu 8B V1.41048K / 16.1 GB1010
...raLong 1M Instruct Abliterated1048K / 32.1 GB49
...a 3.1 8B UltraLong 1M Instruct1048K / 32.1 GB138729
...otron 8B UltraLong 1M Instruct1048K / 32.1 GB70259
...xis Bookwriter Llama3.1 8B Sft1048K / 16.1 GB254
Note: green Score (e.g. "73.2") means that the model is better than Undi95/Unholy-8B-DPO-OAS.