whoashish115/Kitsune-Tales-E4B-EN
Partial fine-tune vs google/gemma-4-E4B-it. Partial change: 50% of the weights changed (attention, mlp, other), in 42 of 42 layers.
Tensors changed: MLP 126/606, Norms 0/484, other 85/261, Attention 132/719, Embeddings 0/6
3 derivatives checked
- mradermacher/Kitsune-Tales-E4B-EN-i1-GGUF: Quantization (fewer layers)
- mradermacher/Kitsune-Tales-E4B-EN-GGUF: Same weights, converted (fewer layers)
- whoashish115/Kitsune-Tales-E4B-EN-GGUF: Quantization (fewer layers)