automerger/YamM7-7B
Full fine-tune vs liminerity/M7-7b. Fine-tune: 97% of the weights changed, across 32 of 32 layers.
Tensors changed: MLP 93/96, Attention 124/128, Norms 18/65, Embeddings 1/1, lm_head 1/1
2 derivatives checked
- MaziyarPanahi/YamM7-7B-GGUF: Quantization
- MaziyarPanahi/YamshadowStrangemerges_32_YamM7: Full fine-tune