Reza2kn/Qianfan-OCR-GGUF

Same weights, converted (fewer layers) vs baidu/Qianfan-OCR. Reza2kn/Qianfan-OCR-GGUF matches part of baidu/Qianfan-OCR (399 of its 745 tensors; the rest of baidu/Qianfan-OCR has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → BF16/F32).

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144

On the Hub · Downloads on Model Pulse