MaziyarPanahi/Experiment28M7_MeliodasNeuralsirkrishna

Full fine-tune vs automerger/Experiment28M7-7B. Fine-tune: 97% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 63/65, MLP 93/96, Attention 124/128, lm_head 1/1

1 derivatives checked

• mradermacher/Experiment28M7_MeliodasNeuralsirkrishna-GGUF: Same weights, converted

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse