gemma-2-2b-it-abliterated
2BGemma
from google/gemma-2-2b-it
↓ 45.1K♥ 8830 repos
Gemma3.Novaciano-1B
Gemma3.Novaciano-1B is a Heretic-ablated variant of NovaCorp/Gemma3.Novaciano-1B, published on Hugging Face by NovaCorp. It is 1B parameters, runs on a laptop CPU class and gemma licence. It is distributed across 4 repositories in Transformers, GGUF and GGUF (imatrix) formats, totalling 6.3K downloads.
Specification
- Model name
- Gemma3.Novaciano-1B
- Source repository
- NovaCorp/Gemma3.Novaciano-1B
- Base model
- NovaCorp/Gemma3.Novaciano-1B
- Publisher
- NovaCorp
- Parameters
- 1B
- Hardware class
- Under 4B — runs on a laptop CPU
- Licence
- gemma
- Task
- Text generation
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- Transformers, GGUF, GGUF (imatrix)
- First indexed
- 12 Aug 2026
- Last updated
- 12 Aug 2026
Ablation technique
How Gemma3.Novaciano-1B 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
“This is a merge of pre-trained language models created using mergekit.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download mradermacher/Gemma3.Novaciano-1B-i1-GGUF --local-dir ./gemma3.novaciano-1b
llama-cli -m ./gemma3.novaciano-1b/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "NovaCorp/Gemma3.Novaciano-1B"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve NovaCorp/Gemma3.Novaciano-1B --trust-remote-codeDownloads and variants (3)
Every published repository of Gemma3.Novaciano-1B, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| mradermacher/Gemma3.Novaciano-1B-i1-GGUF | GGUF (imatrix) | 4.9K |
| mradermacher/Gemma3.Novaciano-1B-GGUF | GGUF | 909 |
| NovaCorp/Gemma3.Novaciano-1Bsource | Transformers | 437 |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Gemma3.Novaciano-1B 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 NovaCorp/Gemma3.Novaciano-1B, not added by ablation — at 1B 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 gemma, but the terms that bind you are NovaCorp/Gemma3.Novaciano-1B’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 Gemma3.Novaciano-1B is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with NovaCorp, and does not independently verify publisher claims. See responsible use.