mergekit-community/L3.1-Romes-Ninomos-Maxxing

Full fine-tune vs djuna/L3.1-Romes-Ninomos. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

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

1 derivatives checked

• mradermacher/L3.1-Romes-Ninomos-Maxxing-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse