Ornith-1.5-9B-abliterated
9BOrnith
from ornith-ai/Ornith-1.5-9B
↓ 140.9K♥ 2724 repos
Ornith-1.5-9B-OBLITERATED
Ornith-1.5-9B-OBLITERATED is a abliterated and uncensored variant of ornith-ai/Ornith-1.5-9B, published on Hugging Face by OBLITERATUS. It is 9B parameters, single consumer GPU class and mit licence. It is distributed across 7 repositories in GGUF, GGUF (imatrix) and Full precision formats, totalling 147.6K downloads.
Specification
- Model name
- Ornith-1.5-9B-OBLITERATED
- Source repository
- OBLITERATUS/Ornith-1.5-9B-OBLITERATED
- Base model
- ornith-ai/Ornith-1.5-9B
- Publisher
- OBLITERATUS
- 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
- GGUF, GGUF (imatrix), Full precision
- First indexed
- 27 Aug 2026
- Last updated
- 1 Sept 2026
Ablation technique
How Ornith-1.5-9B-OBLITERATED was modified, and what that implies.
Abliteration + uncensored fine-tune
Directional ablation combined with additional fine-tuning on unfiltered data, so behaviour diverges from the base model beyond refusal removal alone.
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
“Abliterated version of Ornith-1.5-9B by OBLITERATUS. Safety alignment removed via precision abliteration surgery — the model responds to most prompts without refusal.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download OBLITERATUS/Ornith-1.5-9B-OBLITERATED --local-dir ./ornith-1.5-9b-obliterated
llama-cli -m ./ornith-1.5-9b-obliterated/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "OBLITERATUS/Ornith-1.5-9B-OBLITERATED"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve OBLITERATUS/Ornith-1.5-9B-OBLITERATED --trust-remote-codeDownloads and variants (6)
Every published repository of Ornith-1.5-9B-OBLITERATED, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| OBLITERATUS/Ornith-1.5-9B-OBLITERATEDsource | GGUF | 139.9K |
| mradermacher/Ornith-1.5-9B-OBLITERATED-i1-GGUF | GGUF (imatrix) | 2.9K |
| mradermacher/Ornith-1.5-9B-OBLITERATED-GGUF | GGUF | 2.2K |
| 0xSojalSec/Ornith-1.5-9B-OBLITERATED | GGUF | 1.4K |
| 1Thugga17/Ornith-1.5-9B-OBLITERATED | GGUF | 1.1K |
| Mantisec/Ornith-1.5-9B-OBLITERATED-FP16 | Full precision | 17 |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Ornith-1.5-9B-OBLITERATED 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-1.5-9B, 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.
- This release adds fine-tuning on unfiltered data, so its behaviour diverges from the base model beyond refusal removal — differences you measure cannot be attributed to ablation alone.
- Declared licence is mit, but the terms that bind you are ornith-ai/Ornith-1.5-9B’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-1.5-9B-OBLITERATED is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with OBLITERATUS, and does not independently verify publisher claims. See responsible use.