prithivMLmods/Qwen2-VL-OCR-2B-Instruct-GGUF

Same weights, converted (fewer layers) vs prithivMLmods/Qwen2-VL-OCR-2B-Instruct. prithivMLmods/Qwen2-VL-OCR-2B-Instruct-GGUF matches part of prithivMLmods/Qwen2-VL-OCR-2B-Instruct (338 of its 729 tensors; the rest of prithivMLmods/Qwen2-VL-OCR-2B-Instruct has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/196

On the Hub · Downloads on Model Pulse