automerger/ShadowNeuralsirkrishna-7B
Full fine-tune vs CorticalStack/shadow-clown-7B-slerp. Fine-tune: 97% of the weights changed, across 32 of 32 layers.
Tensors changed: MLP 93/96, Attention 124/128, Norms 65/65, Embeddings 1/1, lm_head 1/1
2 derivatives checked
- MaziyarPanahi/ShadowNeuralsirkrishna-7B-GGUF: Quantization
- MaziyarPanahi/YamshadowStrangemerges_32_ShadowNeuralsirkrishna: Full fine-tune