huihui-ai/Huihui-gemma-3n-E4B-it-abliterated
Partial fine-tune vs google/gemma-3n-E4B-it. Partial change: 19% of the weights changed (attention, mlp, other), in 35 of 35 layers.
Tensors changed: Attention 98/363, Embeddings 0/25, Norms 0/489, other 91/686, MLP 35/112
8 derivatives checked
- bartowski/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-GGUF: Same weights, converted (fewer layers)
- mradermacher/Huihui-gemma-3n-E4B-it-abliterated-GGUF: Same weights, converted (fewer layers)
- mradermacher/Huihui-gemma-3n-E4B-it-abliterated-i1-GGUF: Quantization (fewer layers)
- mlx-community/Huihui-gemma-3n-E4B-it-abliterated-lm-8bit: Quantization
- Qwe1325/Huihui-gemma-3n-E4B-it-abliterated-GGUF: Same weights, converted (fewer layers)
- matrixportalx/Huihui-gemma-3n-E4B-it-abliterated-Q4_K_M-GGUF: Quantization (fewer layers)
- BernTheCreator/Huihui-gemma-3n-E4B-it-abliterated-Q4_0-GGUF: Quantization (fewer layers)
- mlx-community/Huihui-gemma-3n-E4B-it-abliterated-lm-4bit: Quantization