Du hast einen ComfyUI-Workflow? Erstelle direkt im Browser eine verständliche Workflow-Dokumentation.Workflow verständlich machen.Jetzt ausprobieren ↗
This is an uncensored version of google/gemma-4-12B-it-qat-q40-unquantized created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to...
Modellquelle
Quellenbeschreibung
This is an uncensored version of google/gemma-4-12B-it-qat-q4_0-unquantized 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.
: For this model, both the thinking mode and the non-thinking mode have been completely abliterated. Only layers 23-36 have been abliterated.
Quellen
1 QuelleVerifiziert 16. Aug.
Modellartefakte
4 ArtefakteHuihui-gemma-4-12B-it-qat-q4_0-unquantized-abliterated-bf16.gguf
gguf · 22,2 GB · SHA-256 dc273aa74ac7…4f0c · Hugging Face
HerunterladenHuihui-gemma-4-12B-it-qat-q4_0-unquantized-abliterated-Q4_K.gguf
gguf · 6,87 GB · SHA-256 8cfe39c96b96…da6b · Hugging Face
HerunterladenQuellenauszüge
2 AuszügePlease use the latest version of ollama
You can use huihui_ai/gemma-4-abliterated:12b-qat directly,
ollama run huihui_ai/gemma-4-abliterated:12b-qat
Please use the latest version of ggml-org/llama.cpp
apt-get update
apt-get install pciutils build-essential cmake curl libcurl4-openssl-dev -y
git clone https://github.com/ggml-org/llama.cpp
cmake llama.cpp -B llama.cpp/build \
-DBUILD_SHARED_LIBS=OFF -DGGML_CUDA=ON
cmake --build llama.cpp/build --config Release -j --clean-first --target llama-cli llama-mtmd-cli llama-server llama-gguf-split
cp llama.cpp/build/bin/llama-* llama.cpp
./llama.cpp/llama-cli \
-m huihui-ai/Huihui-gemma-4-12B-it-qat-q4_0-unquantized-abliterated-GGUF/Huihui-gemma-4-12B-it-qat-q4_0-unquantized-abliterated-Q4_K.gguf \
-ngl 99 -c 262144 \
--spec-type draft-mtp \
--spec-draft-n-max 4 \
--spec-draft-model huihui-ai/Huihui-gemma-4-12B-it-qat-q4_0-unquantized-abliterated-GGUF/mtp-ggml-model-bf16.gguf
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.
bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge
--- --- 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: - google/gemma-4-12B-it-qat-q4_0-unquantized tags: - abliterated - uncensored - GGUF - MTP --- # huihui-ai/Huihui-gemma-4-12B-it-qat-q4_0-unquantized-abliterated-GGUF This is an uncensored version of [google/gemma-4-12B-it-qat-q4_0-unquantized](https://huggingface.co/google/gemma-4-12B-it-qat-q4_0-unquantized) created with abliteration (see [remove-refusals-with-transformers](https://github.com/Sumandora/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 23-36 have been abliterated. ## ollama Please use the latest version of [ollama](https://github.com/ollama/ollama/releases/) You can use [huihui_ai/gemma-4-abliterated:12b-qat](https://ollama.com/huihui_ai/gemma-4-abliterated:12b-qat) directly, ``` ollama run huihui_ai/gemma-4-abliterated:12b-qat ``` ## GGUF Please use the latest version of [ggml-org/llama.cpp](https://github.com/ggml-org/llama.cpp/releases) ``` apt-get update apt-get install pciutils build-essential cmake curl libcurl4-openssl-dev -y git clone https://github.com/ggml-org/llama.cpp cmake llama.cpp -B llama.cpp/build \ -DBUILD_SHARED_LIBS=OFF -DGGML_CUDA=ON cmake --build llama.cpp/build --config Release -j --clean-first --target llama-cli llama-mtmd-cli llama-server llama-gguf-split cp llama.cpp/build/bin/llama-* llama.cpp ``` ``` ./llama.cpp/llama-cli \ -m huihui-ai/Huihui-gemma-4-12B-it-qat-q4_0-unquantized-abliterated-GGUF/Huihui-gemma-4-12B-it-qat-q4_0-unquantized-abliterated-Q4_K.gguf \ -ngl 99 -c 262144 \ --spec-type draft-mtp \ --spec-draft-n-max 4 \ --spec-draft-model huihui-ai/Huihui-gemma-4-12B-it-qat-q4_0-unquantized-abliterated-GGUF/mtp-ggml-model-bf16.gguf ``` ### 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’...
Source context: 42 downloads · 0 likes · Pipeline any-to-any · Library transformers · Repo tinybiggames/Huihui-gemma-4-12B-it-qat-q4_0-unquantized-abliterated-GGUF