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 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.
Maya Patch
This time the 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 in the Maya directory.
Strata Patch
This time the 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 in the 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.
If you want to run it under b11870 or newer, please refer to the 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 in the unsloth directory.
Unsloth
The UD- series come from 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 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!