krutrim-ai-labs/Chitrapathak-2

Full fine-tune vs nanonets/Nanonets-OCR2-3B. Fine-tune: 100% of the weights changed, across 36 of 36 layers.

Tensors changed: Embeddings 2/2, Norms 129/138, MLP 304/304, Attention 380/380

1 derivatives checked

• mradermacher/Chitrapathak-2-GGUF: Same weights, converted (fewer layers)

On the Hub · Downloads on Model Pulse