| Parameter | Value | | directionindex | 17.62 | | attn.oproj.maxweight | 1.46 | | attn.oproj.maxweightposition | 21.11 | | attn.oproj.minweight | 0.07 | | attn.oproj.minweightdistance | 10.68 | |...
Source du modèle
Extrait de la source
| Parameter | Value | | directionindex | 17.62 | | attn.oproj.maxweight | 1.46 | | attn.oproj.maxweightposition | 21.11 | | attn.oproj.minweight | 0.07 | | attn.oproj.minweightdistance | 10.68 | |...
Sources
1 sourceVérifié 15 sept.
Artefacts du modèle
1 artefactadapter_model.safetensors
safetensors · 2,05 MB · SHA-256 718fa63c542d…e412 · Hugging Face
TéléchargerExtraits de sources
2 extraits--- library_name: transformers license: apache-2.0 license_link: https://ai.google.dev/gemma/docs/gemma_4_license pipeline_tag: any-to-any tags: - heretic - uncensored - decensored - abliterated --- # This is a decensored version of [google/gemma-4-E2B-it](https://huggingface.co/google/gemma-4-E2B-it), made using [Heretic](https://github.com/p-e-w/heretic) v1.2.0 ## Abliteration parameters | Parameter | Value | | :-------- | :---: | | **direction_index** | 17.62 | | **attn.o_proj.max_weight** | 1.46 | | **attn.o_proj.max_weight_position** | 21.11 | | **attn.o_proj.min_weight** | 0.07 | | **attn.o_proj.min_weight_distance** | 10.68 | | **mlp.down_proj.max_weight** | 1.36 | | **mlp.down_proj.max_weight_position** | 25.45 | | **mlp.down_proj.min_weight** | 1.07 | | **mlp.down_proj.min_weight_distance** | 17.06 | ## Performance | Metric | This model | Original model ([google/gemma-4-E2B-it](https://huggingface.co/google/gemma-4-E2B-it)) | | :----- | :--------: | :---------------------------: | | **KL divergence** | 0.1693 | 0 *(by definition)* | | **Refusals** | 14/100 | 99/100 | ----- <div align="center"> <img src=https://ai.google.dev/gemma/images/gemma4_banner.png> </div> <p align="center"> <a href="https://huggingface.co/collections/google/gemma-4" target="_blank">Hugging Face</a> | <a href="https://github.com/google-gemma" target="_blank">GitHub</a> | <a href="https://blog.google/innovation-and-ai/technology/developers-tools/gemma-4/" target="_blank">Launch Blog</a> | <a href="https://ai.google.dev/gemma/docs/core" target="_blank">Documentation</a> <br> <b>License</b>: <a href="https://ai.google.dev/gemma/docs/gemma_4_license" target="_blank">Apache 2.0</a> | <b>Authors</b>: <a href="https://deepmind.google/models/gemma/" target="_blank">Google DeepMind</a> </p> Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on small models) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants. Gemma 4 features a context window of up to 256K tokens and maintains multilingual support in over 140 languages. Featuring both Dense and Mixture-of-Experts (MoE) architectures, Gemma 4 is well-suited for tasks like text generation, coding, and reasoning. The models are available in four distinct sizes: *...
Source context: 0 downloads · 0 likes · Pipeline any-to-any · Library transformers · Repo anrp/gemma-4-E2B-it-heretic-tryloraup