Ornith-1.5-35B-A3B-Uncensored
35BOrnithuncensored
from ornith-ai/Ornith-1.5-35B-A3B
↓ 100.3K♥ 2918 repos
Ornith-1.5-35B-A3B-abliterated
Ornith-1.5-35B-A3B-abliterated is a refusal-ablated variant of ornith-ai/Ornith-1.5-35B-A3B, published on Hugging Face by huihui-ai. It is 35B total parameters (mixture-of-experts), 48GB VRAM class class and mit licence. The publisher states that layers 11–29 were ablated, leaving the remaining layers unmodified. It is distributed across 19 repositories in GGUF, Transformers, GGUF (imatrix) and MLX formats, totalling 139.5K downloads.
Specification
- Model name
- Ornith-1.5-35B-A3B-abliterated
- Source repository
- huihui-ai/Huihui-Ornith-1.5-35B-A3B-abliterated
- Base model
- ornith-ai/Ornith-1.5-35B-A3B
- Publisher
- huihui-ai
- Parameters
- 35B (mixture-of-experts)
- Hardware class
- 25B – 50B — 48GB VRAM class
- Licence
- mit
- Task
- Text generation
- Context window
- Not documented
- Ablation scope
- Layers 11–29
- Formats available
- GGUF, Transformers, GGUF (imatrix), MLX
- First indexed
- 20 Aug 2026
- Last updated
- 30 Aug 2026
Ablation technique
How Ornith-1.5-35B-A3B-abliterated was modified, and what that implies.
Abliteration (directional ablation)
The single residual-stream direction that mediates refusal is identified from harmful/harmless prompt pairs and projected out of the model weights.
Reported scope: Layers 11–29. This comes from the publisher’s own model card and has not been independently verified.
From the publisher’s model card
“This is an uncensored version of ornith-ai/Ornith-1.5-35B-A3B created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-GGUF --local-dir ./ornith-1.5-35b-a3b-abliterated
llama-cli -m ./ornith-1.5-35b-a3b-abliterated/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "huihui-ai/Huihui-Ornith-1.5-35B-A3B-abliterated"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve huihui-ai/Huihui-Ornith-1.5-35B-A3B-abliterated --trust-remote-codeDownloads and variants (18)
Every published repository of Ornith-1.5-35B-A3B-abliterated, including quantised re-releases by other authors.
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Ornith-1.5-35B-A3B-abliterated will attempt offensive-security prompts that a hosted commercial model declines, which is what makes it usable for red-team corpus generation and for measuring what an unaligned model of this class produces.
- Capability is inherited from ornith-ai/Ornith-1.5-35B-A3B, not added by ablation — at 35B parameters, expect roughly the base model’s competence, minus some instruction-following fidelity.
- Ablation is reported as limited to layers 11–29, so untouched layers may still reassert refusal on some phrasings.
- Declared licence is mit, but the terms that bind you are ornith-ai/Ornith-1.5-35B-A3B’s — a re-release cannot grant more than its parent.
Handling: run it isolated, put moderation in front of it if anyone outside your team can reach it, and verify the weights before loading — these are third-party artifacts. Full handling and licence guidance.
Metadata for Ornith-1.5-35B-A3B-abliterated is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with huihui-ai, and does not independently verify publisher claims. See responsible use.