Ornith-1.0-9B-Uncensored
9BOrnithuncensored
from deepreinforce-ai/Ornith-1.0-9B
↓ 10.5K♥ 104 repos
Ornith-1.0-9B-heretic
Ornith-1.0-9B-heretic is a Heretic-ablated variant of deepreinforce-ai/Ornith-1.0-9B, published on Hugging Face by SC117. It is 9B parameters, single consumer GPU class and mit licence. It is distributed across 7 repositories in Transformers, GGUF and GGUF (imatrix) formats, totalling 5.9K downloads.
Specification
- Model name
- Ornith-1.0-9B-heretic
- Source repository
- SC117/Ornith-1.0-9B-heretic-MTP
- Base model
- deepreinforce-ai/Ornith-1.0-9B
- Publisher
- SC117
- Parameters
- 9B
- Hardware class
- 4B – 10B — single consumer GPU
- Licence
- mit
- Task
- Text generation
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- Transformers, GGUF, GGUF (imatrix)
- First indexed
- 29 Jun 2026
- Last updated
- 5 Aug 2026
Ablation technique
How Ornith-1.0-9B-heretic was modified, and what that implies.
Heretic
Automated directional ablation via the Heretic toolchain, which searches for the refusal direction and applies it with a KL-divergence budget so general capability is preserved.
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 a self-improving agentic coding model from DeepReinforce AI, post-trained on top of Qwen3.5 (9B Dense) with RL to jointly optimize scaffold generation and solution rollouts. It achieves strong performance on Terminal-Bench 2.1, SWE-Bench Verified, NL2Repo, and OpenClaw among open-source models of...”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download SC117/Ornith-1.0-9B-heretic-MTP-GGUF --local-dir ./ornith-1.0-9b-heretic
llama-cli -m ./ornith-1.0-9b-heretic/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "SC117/Ornith-1.0-9B-heretic-MTP"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve SC117/Ornith-1.0-9B-heretic-MTP --trust-remote-codeDownloads and variants (6)
Every published repository of Ornith-1.0-9B-heretic, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| SC117/Ornith-1.0-9B-heretic-MTP-GGUF | GGUF | 4.4K |
| mradermacher/Ornith-1.0-9B-heretic-MTP-i1-GGUF | GGUF (imatrix) | 753 |
| mradermacher/Ornith-1.0-9B-heretic-MTP-GGUF | GGUF | 426 |
| SC117/Ornith-1.0-9B-heretic-MTPsource | Transformers | 178 |
| trohrbaugh/Ornith-1.0-9B-heretic | Transformers | 74 |
| Toaster496/Ornith-1.0-9B-heretic | Transformers | 12 |
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-heretic 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-heretic is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with SC117, and does not independently verify publisher claims. See responsible use.