Ornith-1.0-9B-Uncensored
9BOrnithuncensored
from deepreinforce-ai/Ornith-1.0-9B
↓ 10.5K♥ 104 repos
Ornith-1.0-9B-abliterated
Ornith-1.0-9B-abliterated is a refusal-ablated variant of deepreinforce-ai/Ornith-1.0-9B, published on Hugging Face by PinoCookie. It is 9B parameters, single consumer GPU class and mit licence. It is distributed across 6 repositories in NVFP4, GGUF, MLX and Transformers formats, totalling 10.2K downloads.
Specification
- Model name
- Ornith-1.0-9B-abliterated
- Source repository
- PinoCookie/Ornith-1.0-9B-abliterated
- Base model
- deepreinforce-ai/Ornith-1.0-9B
- Publisher
- PinoCookie
- Parameters
- 9B
- Hardware class
- 4B – 10B — single consumer GPU
- Licence
- mit
- Task
- Text generation
- Context window
- 262K tokens (as documented)
- Ablation scope
- Not stated by the publisher
- Formats available
- NVFP4, GGUF, MLX, Transformers
- First indexed
- 30 Jun 2026
- Last updated
- 4 Aug 2026
Ablation technique
How Ornith-1.0-9B-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: Not stated by the publisher. Publishers frequently omit this, so verify behaviour empirically rather than assuming full coverage.
From the publisher’s model card
“Ornith-1.0-9B is DeepReinforce AI's agentic coding model, a dense 9B transformer post-trained on Qwen 3.5. It's designed for autonomous code generation, tool calling, and long-context agentic workflows (262K context length).”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download huihui-ai/Huihui-Ornith-1.0-9B-abliterated-MTP-GGUF --local-dir ./ornith-1.0-9b-abliterated
llama-cli -m ./ornith-1.0-9b-abliterated/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "PinoCookie/Ornith-1.0-9B-abliterated"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve PinoCookie/Ornith-1.0-9B-abliterated --trust-remote-codeDownloads and variants (5)
Every published repository of Ornith-1.0-9B-abliterated, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| huihui-ai/Huihui-Ornith-1.0-9B-abliterated-MTP-GGUF | GGUF | 9.6K |
| maci0/Ornith-1.0-9B-abliterated-NVFP4 | NVFP4 | 401 |
| Dzluck/Ornith-1.0-9B-abliterated-MTP-GGUF | GGUF | 142 |
| Shiftedx/ornith-1.0-9b-abliterated-mxfp4-mlx | MLX | 95 |
| PinoCookie/Ornith-1.0-9B-abliteratedsource | Transformers | 9 |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Ornith-1.0-9B-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 deepreinforce-ai/Ornith-1.0-9B, not added by ablation — at 9B parameters, expect a small model’s reasoning and a high error rate on exploit detail.
- The publisher does not state which layers were ablated, so assume nothing about refusal consistency — probe it directly.
- Declared licence is mit, but the terms that bind you are deepreinforce-ai/Ornith-1.0-9B’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-1.0-9B-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 PinoCookie, and does not independently verify publisher claims. See responsible use.