automerger/Strangemerges_32Strangemerges_30-7B
Full fine-tune vs Gille/StrangeMerges_30-7B-slerp. Fine-tune: 97% of the weights changed, across 32 of 32 layers.
Tensors changed: MLP 93/96, Attention 124/128, Norms 12/65, Embeddings 1/1, lm_head 1/1
1 derivatives checked
- MaziyarPanahi/Strangemerges_32Strangemerges_30-7B-GGUF: Quantization