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-4-31B-it
tags: - abliterated
- uncensored
huihui-ai/Huihui-gemma-4-31B-it-abliterated-v2
This is an uncensored version of google/gemma-4-31B-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 This is the new version, the first 5 layers have not been abliterated, with fewer warnings and rejections. You can refer to the PPL values below, which are lower than those of the original model:
| model | PPL | Gap |
|---|---|---|
| google/gemma-4-31B-it/ggml-model-f16.gguf | PPL = 14874.7532 +/- 272.53240 | + 0 |
| huihui-ai/Huihui-gemma-4-31B-it-abliterated/ggml-model-f16.gguf | PPL = 13335.5546 +/- 239.28283 | - 1,539.1986 |
| huihui-ai/Huihui-gemma-4-31B-it-abliterated-v2/ggml-model-f16.gguf | PPL = 13161.2940 +/- 236.60548 | - 1,713.4592 - 174.2606 |
The smaller the PPL value, the higher the model quality.
PPL value test command
llama-perplexity gemma-4-31B-it/ggml-model-f16.gguf -c 8192 -b 512 -ctk bf16 -ctv bf16 -f wiki.test.raw
References
llama-perplexity
llama.cpp-b8740
ollama
Please use the latest version of ollama
You can use huihui_ai/gemma-4-abliterated:31B-v2 directly,
ollama run huihui_ai/gemma-4-abliterated:31b-v2
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!