jeiku/neurodeed

Full fine-tune vs FourOhFour/Deedlit_4B. Fine-tune: 91% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 0/1, Norms 26/65, MLP 96/96, Attention 128/128, lm_head 1/1

1 derivatives checked

• mradermacher/neurodeed-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse