prithivMLmods/Qwen2-VL-OCR2-2B-Instruct

Same weights, repacked vs Qwen/Qwen2-VL-2B-Instruct. Same weights in different files (re-saved, re-sharded or new metadata).

Tensors changed: Embeddings 0/2, Norms 0/187, MLP 0/216, Attention 0/324

2 derivatives checked

• mradermacher/Qwen2-VL-OCR2-2B-Instruct-GGUF: Same weights, converted (fewer layers)
• DevQuasar/prithivMLmods.Qwen2-VL-OCR2-2B-Instruct-GGUF: Same weights, converted (fewer layers)

18 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse