djuna/L3.1-Romes-Ninomos

Full fine-tune vs Edgerunners/Lyraea-large-llama-3.1. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

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

3 derivatives checked

• mradermacher/L3.1-Romes-Ninomos-GGUF: Same weights, converted
• mradermacher/L3.1-Romes-Ninomos-i1-GGUF: Quantization
• mergekit-community/L3.1-Romes-Ninomos-Maxxing: Full fine-tune

On the Hub · Downloads on Model Pulse