mlabonne / Model details
gemma-3-1b-it-abliterated-v2-GGUF
mlabonne/gemma-3-1b-it-abliterated-v2-GGUF
About this model
This repository by mlabonne provides GGUF weights for mlabonne/gemma3-1b-it-abliterated-v2, an abliterated derivative of google/gemma-3-1b-it. The creator describes the underlying model as an uncensored version made with a new abliteration technique that targets refusals with enhanced accuracy. According to the model card, the refusal direction is computed by comparing residual streams between harmful and harmless samples, and hidden states of target modules are orthogonalized to subtract that direction. The creator says a hybrid evaluation with a dedicated test set is used to calculate an acceptance rate, with a goal above 90% while retaining coherent outputs. The weights are provided in GGUF format under the gemma license.
Description sources
Source-based description, not an independent evaluation. Check the linked sources for the creator’s claims and limitations.
Size and formats
- Base model
- mlabonne/gemma3-1b-it-abliterated-v2
- Parameters
- Unknown
- Main repository formats
- GGUF
- License tag
- gemma
- Languages
- Unknown
- Last updated
- 2025-05-29 · 10:59:07.000 UTC
What changed
Model types are creator-reported, not independently tested. These labels describe source metadata, not a guarantee of behavior.
- abliteratedmodel name:
gemma-3-1b-it-abliterated-v2-GGUF
Family evidence
These groupings are source-reported. Explicit base identifiers take priority over generic architecture tags.
- Gemma: Base model: mlabonne/gemma3-1b-it-abliterated-v2
Available versions
Versions appear here only when they explicitly name this exact model as their source. Check each repository for available files.
- Main repository files ↗GGUF
- No other explicitly linked versions recorded.
Customize or build on this model
Listed from public GitHub data, not tested by us. Read the code and license before you run anything.
Tools to customize it further
Make a smaller download (quantize)
- llama.cpp ↗ ★ 132,124
Runs models locally and includes the tools behind most GGUF files. A conversion script turns Hugging Face weights into GGUF, and llama-quantize shrinks a high-precision GGUF to lower-bit formats, which can cost some accuracy.
Learn the techniques
- LLM Course ↗ ★ 84,633
A free course with roadmaps and Colab notebooks. Its notebooks include one-click tools for merging with MergeKit, quantizing to GGUF, GPTQ, EXL2, AWQ and HQQ, and automatic abliteration with custom datasets.
Source provenance
- Downloads
- 1,235
- Likes
- 7
- Metadata checked
- 2026-10-24 · 12:14:47 UTC
- First seen in index
- 2026-10-24 · 12:14:47 UTC
- Source revision
- 9a6d4c073898f0111db2ab65983505196d87704a
Source-card excerpt
Source model card excerpt: 💎 Gemma 3 1B IT Abliterated GGUF Gemma 3 Abliterated GGUF 1B • 4B • 12B • 27B This is an uncensored version of
From mlabonne/gemma-3-1b-it-abliterated-v2-GGUF. Creator model-card excerpt, not an independent review.
Inspect before you run
Low refusal is not proof of correctness. Outputs can be inaccurate, harmful, or biased. Review the model card, license and files yourself. A license tag is not commercial-use advice. Parameter counts are source metadata; no hardware compatibility is implied.
This directory does not run, host, redistribute, or test model weights.
Collection rules & limitations ↗