prithivMLmods/LightOnOCR-2-1B-f32-GGUF

Same weights, converted (fewer layers) vs lightonai/LightOnOCR-2-1B. prithivMLmods/LightOnOCR-2-1B-f32-GGUF matches part of lightonai/LightOnOCR-2-1B (310 of its 532 tensors; the rest of lightonai/LightOnOCR-2-1B has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/113, MLP 0/84, Attention 0/112

On the Hub · Downloads on Model Pulse