ahmadw/jina-ocr-v1-GGUF

Same weights, converted vs jinaai/jina-ocr-v1. Same weights stored in another dtype (BF16 → F16/F32), plus 33 new tensors.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/25, MLP 0/47, Attention 0/48

On the Hub · Downloads on Model Pulse