AurelPx/Meliodas-7b-dare
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 18/65, MLP 89/96, Attention 120/128, lm_head 1/1
8 derivatives checked
- mradermacher/Meliodas-7b-dare-GGUF: Quantization
- automerger/MeliodasPercival_01-7B: Full fine-tune
- automerger/Experiment28Meliodas-7B: Full fine-tune
- automerger/CalmexperimentMeliodas-7B: Full fine-tune
- automerger/ShadowMeliodas-7B: Full fine-tune
- automerger/MeliodasNeuralsirkrishna-7B: Full fine-tune
- automerger/NeuralsynthesisMeliodas-7B: Full fine-tune
- automerger/MeliodasM7-7B: Full fine-tune