SzilviaB/Gemma_Delirium_9B
Partial fine-tune vs DavidAU/Gemma-The-Writer-9B. Partial change: 78% of the weights changed (attention, mlp, norms), in 40 of 42 layers.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 81/169, MLP 120/126, Attention 160/168
2 derivatives checked
- mradermacher/Gemma_Delirium_9B-i1-GGUF: Quantization
- mradermacher/Gemma_Delirium_9B-GGUF: Same weights, converted
2 other repos hold byte-for-byte identical weight files.