MaziyarPanahi/MeliodasPercival_01_T3qExperiment26
Full fine-tune vs automerger/MeliodasPercival_01-7B. 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
- mradermacher/MeliodasPercival_01_T3qExperiment26-GGUF: Same weights, converted