--- license: mit library_name: transformers pipeline_tag: image-text-to-text base_model: deepseek-ai/DeepSeek-V4.1-Flash-1017 tags: - deepseek - deepseek_v41 - unsloth - abliterated - uncensored - huihui - gguf - gsq - rco - quantization - mixed-precision - ist-daslab - moe - Strata - Maya - imatrix - mixture-of-experts - project-maya --- # huihui-ai/Huihui-DeepSeek-V4.1-Flash-1017-abliterated-GGUF This is an uncensored version of [deepseek-ai/DeepSeek-V4.1-Flash-1017](https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017) created with abliteration. This ablation was performed entirely using llama.cpp's GGUF model, without relying on Transformers, For the specific ablation method, please refer to [cvector-generator](https://github.com/ggml-org/llama.cpp/blob/master/tools/cvector-generator/README.md). ## patch-Strata-GSQ-RCO-Coder The **patch-Strata-GSQ-RCO-Coder** here can patch the latest patch for the latest [ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-Coder-GGUF](https://huggingface.co/ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-Coder-GGUF) versions of **IQ2_XXS**, for the **ISTA-DAS Coder** of DeepSeek-V4.1-Flash-1017 in **Strata**, which saves storage space; you need to run the command yourself to apply the patch. For details, Please refer to [README-patch-Strata.md](patch-Strata-GSQ-RCO-Coder/README-patch-Strata.md) in the [patch-Strata-GSQ-RCO-Coder](https://huggingface.co/huihui-ai/Huihui-DeepSeek-V4.1-Flash-1017-abliterated-GGUF/tree/main/patch-Strata-GSQ-RCO-Coder) directory. ## patch-unsloth-Q2 We have released the latest patch for the latest [unsloth/DeepSeek-V4.1-Flash-1017-GGUF](https://huggingface.co/unsloth/DeepSeek-V4.1-Flash-1017-GGUF) versions of **UD-IQ1_M**,**UD-IQ1_S**,**UD-IQ2_XXS**, and **UD-Q2_K_XL**, which saves storage space; you need to run the command yourself to apply the patch. For details, Please refer to [README-patch-unsloth.md](patch-unsloth-Q2/README-patch-unsloth.md) in the [patch-unsloth-Q2](https://huggingface.co/huihui-ai/Huihui-DeepSeek-V4.1-Flash-1017-abliterated-GGUF/tree/main/patch-unsloth-Q2) directory. ## Maya Patch This time the [Maya](https://github.com/mw00/project-maya) weights are not provided directly; you need to run the command yourself to apply the patch. For details, Please refer to [README-Maya.md](Maya/README-Maya.md) in the [Maya](https://huggingface.co/huihui-ai/Huihui-DeepSeek-V4.1-Flash-1017-abliterated-GGUF/tree/main/Maya) directory. ## Strata Patch This time the [Strata](https://github.com/Niko1221/Strata) weights are not provided directly; you need to run the command yourself to apply the patch. For details, Please refer to [README-Strata.md](Strata-deepseek-v4.1-flash-IST-DAS/README-Strata.md) in the [Strata-deepseek-v4.1-flash-IST-DAS](https://huggingface.co/huihui-ai/Huihui-DeepSeek-V4.1-Flash-1017-abliterated-GGUF/tree/main/Strata-deepseek-v4.1-flash-IST-DAS) directory. This portion of the weights actually comes from [TA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF](https://huggingface.co/ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF). If you want to run it under [b11870](https://github.com/ggml-org/llama.cpp/releases/tag/b11870) or newer, please refer to the [llamacpp](https://huggingface.co/ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF/blob/main/README.md#llamacpp) instructions for the necessary modifications. ## Unsloth Patch We also convert Unsloth’s other quantized versions to Patch mode, which saves storage space; you need to run the command yourself to apply the patch. For details, Please refer to [README-Unsloth.md](unsloth/README-Unsloth.md) in the [unsloth](https://huggingface.co/huihui-ai/Huihui-DeepSeek-V4.1-Flash-1017-abliterated-GGUF/tree/main/unsloth) directory. ## Unsloth The **UD-** series come from [unsloth/DeepSeek-V4.1-Flash-1017-GGUF](https://huggingface.co/unsloth/DeepSeek-V4.1-Flash-1017-GGUF). Only layers **11 to 28 (0-based indexing)** have been ablated. The expert system was not ablated. Only 18 weights were ablated in total (the 18 attn_output_b tensors); everything else was left untouched. ## llama.cpp Requires llama.cpp [b11870](https://github.com/ggml-org/llama.cpp/releases/tag/b11870) or newer. ``` apt-get update apt-get install pciutils build-essential cmake curl libcurl4-openssl-dev git -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-cli -m huihui-ai/Huihui-DeepSeek-V4.1-Flash-1017-abliterated/UD-IQ1_S/DeepSeek-V4.1-Flash-1017-UD-IQ1_S-00001-of-00005.gguf -c 262144 ``` ### 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](https://ko-fi.com/huihuiai)!