Downloads · 30 days
22
3% of all-time downloads
yasha-8b-abliterated
BeheraBoi/yasha-8b-abliterated
yasha-8b-abliterated is a text generation model from BeheraBoi. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as other.
Base abliterated release. Trained on GLA architecture with MoE 2/16 and ~240K multi-domain samples.
All-time downloads
728
Public
Parameters
9.6B
6.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors25.6 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- other
- Access
- Public
- Created
- Jun 14, 2026
- Updated
- Jun 22, 2026
- SHA
- 24c85406
Try a prompt
Model card
From the Hugging Face model README
Yasha-8B-Abliterated
Base abliterated release. Trained on GLA architecture with MoE 2/16 and ~240K multi-domain samples.
Features
- Abliterated: Orthogonal refusal projection removed from all linear layers
- MoE 2/16: 2 active experts per token, 16 total
- GLA: Gated Linear Attention — O(1) recurrent state, infinite context capability
- Partial RoPE (50%) + YaRN 8x scaling
- Uncensored: No refusal, no guardrails, no alignment filtering
Details
| Param | Value |
|---|---|
| Parameters | ~12.8B total, ~8B active |
| Layers | 80 |
| Hidden | 2048 |
| Heads | 8 × 128d |
| Experts | 16 (top-2) |
| Vocab | 262K |
| Context | 128K native, 1M with YaRN |
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("BeheraBoi/yasha-8b-abliterated")
tokenizer = AutoTokenizer.from_pretrained("BeheraBoi/yasha-8b-abliterated")
- Task
- Text Generation
- Library
- transformers
- License
- other
- Languages
- en
- Created
- Jun 14, 2026
- Updated
- Jun 22, 2026