automerger/Multi_verse_modelM7-7B
Full fine-tune vs MTSAIR/multi_verse_model. Fine-tune: 93% of the weights changed, across 31 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 13/65, MLP 89/96, Attention 120/128, lm_head 1/1
2 derivatives checked
- MaziyarPanahi/Multi_verse_modelM7-7B-GGUF: Quantization
- MaziyarPanahi/YamshadowStrangemerges_32_Multi_verse_modelM7: Full fine-tune