Laxhar/noobai-XL-Vpred-0.75

Partial fine-tune vs Laxhar/noobai-XL-Vpred-0.65. Partial change: 72% of the weights changed (attention, embeddings, norms, other), in 0 of 12 layers.

Tensors changed: other 534/664, Attention 700/716, Norms 442/546, Embeddings 4/590

2 derivatives checked

On the Hub · Downloads on Model Pulse