automerger/Multi_verse_modelExperiment28-7B
Full fine-tune vs MTSAIR/multi_verse_model. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 64/65, MLP 96/96, Attention 128/128, lm_head 1/1
3 derivatives checked
- MaziyarPanahi/Multi_verse_modelExperiment28-7B-GGUF: Quantization
- MaziyarPanahi/YamshadowInex12_Multi_verse_modelExperiment28: Full fine-tune
- MaziyarPanahi/YamshadowStrangemerges_32_Multi_verse_modelExperiment28: Full fine-tune