prithivMLmods/Raptor-X4

Full fine-tune vs prithivMLmods/Viper-Coder-v1.6-r999. Fine-tune: 100% of the weights changed, across 48 of 48 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 97/97, MLP 144/144, Attention 336/336

1 derivatives checked

• DevQuasar-2/prithivMLmods.Raptor-X4-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse