MaziyarPanahi/MeliodasPercival_01_Experiment26T3q
Full fine-tune vs automerger/Experiment26T3q-7B. Fine-tune: 97% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 48/65, MLP 93/96, Attention 124/128, lm_head 1/1
2 derivatives checked
- mradermacher/MeliodasPercival_01_Experiment26T3q-GGUF: Same weights, converted
- automerger/Ognoexperiment27multi_verse_modelMeliodaspercival_01_experiment26t3q-7B: Full fine-tune
1 other repos hold byte-for-byte identical weight files.