automerger/Multi_verse_modelExperiment26-7B
Full fine-tune vs MTSAIR/multi_verse_model. Fine-tune: 97% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 18/65, MLP 93/96, Attention 124/128, lm_head 1/1
1 derivatives checked
- MaziyarPanahi/Multi_verse_modelExperiment26-7B-GGUF: Same weights, converted