library_name: transformers
license: apache-2.0
license_link: https://ai.google.dev/gemma/docs/gemma_4_license
pipeline_tag: any-to-any
base_model:
- huihui-ai/Huihui-gemma-4-12B-it-abliterated
tags: - abliterated
- uncensored
- nvfp4
pekkAi/Gemma-4-12B-it-abliterated-NVFP4
This model pekkAi/Gemma-4-12B-it-abliterated-NVFP4 was quantized to NVFP4 format from huihui-ai/Huihui-gemma-4-12B-it-abliterated using Model-Optimizer.
Static NVFP4 weight scales from MSE FP8-scale sweep and dynamic NVFP4 inputs to MLP/MoE layers, plus FP8 KV-cache cast mode.
Tested working on RTX 5090 32Gb py3.13+torch2.11+cu130
Serving (RTX 5090, 32GB)
sglang serve \
--model-path Gemma-4-12B-it-abliterated-NVFP4 \
--reasoning-parser gemma4 \
--tool-call-parser gemma4 \
--speculative-algorithm NEXTN \
--speculative-draft-model-path google/gemma-4-12B-it-assistant \
--speculative-num-steps 5 \
--speculative-num-draft-tokens 6 \
--speculative-eagle-topk 1 \
--mem-fraction-static 0.85 \
--host 0.0.0.0 --port 30000
Installing SGLang with modelopt-ptq support (Thanks to AxionML)
# Editable install of the branch
git clone https://github.com/bzhng-development/sglang.git
cd sglang && git checkout gemma4-modelopt-ptq
pip install uv
uv pip install ./python --torch-backend cu130 # or other cuXXX version
# transformers with Gemma 4 (encoder-free unified) support
uv pip install transformers -U
Original Model Card
huihui-ai/Huihui-gemma-4-12B-it-abliterated
This is an uncensored version of google/gemma-4-12B-it created with abliteration (see remove-refusals-with-transformers to know more about it).
This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.
Note For this model, both the thinking mode and the non-thinking mode have been completely abliterated. Only layers 23-28 have been abliterated.
Important Notice: The weights of the earliest released google/gemma-4-12B-it model have issues. We have already re-ablated and re-uploaded the model. If you have already downloaded it, please re-download.
Usage Warnings
Risk of Sensitive or Controversial Outputs: This model’s safety filtering has been significantly reduced, potentially generating sensitive, controversial, or inappropriate content. Users should exercise caution and rigorously review generated outputs.
Not Suitable for All Audiences: Due to limited content filtering, the model’s outputs may be inappropriate for public settings, underage users, or applications requiring high security.
Legal and Ethical Responsibilities: Users must ensure their usage complies with local laws and ethical standards. Generated content may carry legal or ethical risks, and users are solely responsible for any consequences.
Research and Experimental Use: It is recommended to use this model for research, testing, or controlled environments, avoiding direct use in production or public-facing commercial applications.
Monitoring and Review Recommendations: Users are strongly advised to monitor model outputs in real-time and conduct manual reviews when necessary to prevent the dissemination of inappropriate content.
No Default Safety Guarantees: Unlike standard models, this model has not undergone rigorous safety optimization. huihui.ai bears no responsibility for any consequences arising from its use.
Donation
Your donation helps us continue our further development and improvement, a cup of coffee can do it.
- bitcoin:
bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge
- Support our work on Ko-fi!