DireDreadlord/Vakya-Mini-Extended-100M

Full fine-tune vs tiiuae/Falcon-H1-Tiny-Multilingual-100M-Instruct. Fine-tune: 100% of the weights changed, across 24 of 24 layers.

Tensors changed: Embeddings 1/1, Norms 0/49, MLP 72/72, other 98/168, Attention 96/96

1 derivatives checked

• mradermacher/Vakya-Mini-Extended-100M-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse