Kwoya/Mini-Spyra-v.3.6

Full fine-tune vs dphn/Dolphin3.0-Llama3.1-8B. Fine-tune: 93% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 0/1, Norms 12/65, MLP 96/96, Attention 128/128, lm_head 1/1

1 derivatives checked

• mradermacher/Mini-Spyra-v.3.6-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse