jeiku/Cookie_7B
Partial fine-tune vs jeiku/Rainbow_69_7B. Partial change: 90% of the weights changed (attention, embeddings, mlp, norms), in 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 1/65, MLP 87/96, Attention 121/128, lm_head 0/1
4 derivatives checked
- mradermacher/Cookie_7B-i1-GGUF: Quantization
- mradermacher/Cookie_7B-GGUF: Same weights, converted
- ChaoticNeutrals/RP_Vision_7B: Full fine-tune
- jeiku/NarrativeNexus_7B: Full fine-tune
1 other repos hold byte-for-byte identical weight files.