automerger/Experiment24Shadow-7B
Full fine-tune vs CorticalStack/shadow-clown-7B-slerp. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: MLP 96/96, Attention 128/128, Norms 50/65, Embeddings 1/1, lm_head 1/1
3 derivatives checked
- MaziyarPanahi/Experiment24Shadow-7B-GGUF: Quantization
- MaziyarPanahi/M7Yamshadowexperiment28_Experiment24Shadow: Full fine-tune
- MaziyarPanahi/MeliodasPercival_01_Experiment24Shadow: Full fine-tune