Downloads · 30 days
57
8% of all-time downloads
Ornith-1.5-35B-A3B-abliterated
pottokao/Ornith-1.5-35B-A3B-abliterated
Ornith-1.5-35B-A3B-abliterated is a text generation model from pottokao. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.
Abliterated (refusal-direction removed) build of ornith-ai/Ornith-1.5-35B-A3B, BF16, 65 GB.
All-time downloads
713
Public
Parameters
34.7B
69.3 GB on disk
Likes
2
Public
Repo makeup
Click a slice to open those files.
.safetensors69.3 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- mit
- Model type
- qwen3_5_moe_text
- Access
- Public
- Created
- Aug 20, 2026
- Updated
- Aug 20, 2026
- SHA
- 8787269d
Try a prompt
Base models
Model card
From the Hugging Face model README
Ornith-1.5-35B-A3B-abliterated
Abliterated (refusal-direction removed) build of
ornith-ai/Ornith-1.5-35B-A3B, BF16, 65 GB.
An NVFP4 quantization of this model (20 GB, runs on 2×16 GB GPUs, with benchmarks) is at
pottokao/Ornith-1.5-35B-A3B-abliterated-NVFP4-DFlash.
⚠️ Text-only. This is a language-model-only export: it contains no vision tower and no MTP head, unlike the original release.
model_typeisqwen3_5_moe_text, architectureQwen3_5MoeForCausalLM.
⚠️ Uncensored. Safety refusal behaviour has been deliberately removed. You are responsible for how you use it.
Method
Classic refusal-direction ablation (orthogonalization), single direction:
| Step | Detail |
|---|---|
| Probe layer | 24 — int(num_layers × 0.6), 40 layers total |
| Samples | 64 harmful + 64 harmless prompts (random.seed(0)), last-token hidden state |
| Direction | d = normalize(mean(harmful) − mean(harmless)) |
| Ablation | For every .o_proj and .down_proj: W ← W − outer(d, dᵀW) |
The refusal direction is projected out of the output space of the attention- and MLP-output
projections, leaving all other weights untouched. Tooling derived from
remove-refusals-with-transformers.
Architecture
Hybrid Mamba + MoE, 40 layers: 30 linear-attention (Mamba-style) layers and 10 full-attention layers (indices 3, 7, …, 39), 256 experts per layer with a shared expert, ~3 B active parameters. Context length 262,144.
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3_5_moe_text
- License
- mit
- Created
- Aug 20, 2026
- Updated
- Aug 20, 2026