DavidAU/Gemma-3-4b-it-Uncensored-DBL-X
Partial fine-tune vs google/gemma-3-4b-it. Partial change: 2% of the weights changed (attention, mlp, norms), in 1 of 34 layers.
Tensors changed: Embeddings 0/4, Norms 7/316, MLP 3/210, Attention 4/352, other 0/1
4 derivatives checked
- DavidAU/Gemma-3-it-4B-Uncensored-DBL-X-GGUF: Same weights, converted (fewer layers)
- DavidAU/Gemma-3-4b-it-MAX-HORROR-Uncensored-DBL-X-Imatrix-GGUF: Quantization (fewer layers)
- mradermacher/Gemma-3-4b-it-Uncensored-DBL-X-i1-GGUF: Quantization (fewer layers)
- mradermacher/Gemma-3-4b-it-Uncensored-DBL-X-GGUF: Same weights, converted (fewer layers)
1 other repos hold byte-for-byte identical weight files.