kranidiotis/ottoman-ocr-qwen2.5-vl-7b

Partial fine-tune vs Qwen/Qwen2.5-VL-7B-Instruct. Partial change: 83% of the weights changed (attention, mlp), in 28 of 32 layers.

Tensors changed: Embeddings 0/2, Norms 0/122, MLP 86/88, Attention 112/324, lm_head 0/1

1 derivatives checked

• mradermacher/ottoman-ocr-qwen2.5-vl-7b-GGUF: Same weights, converted (fewer layers)

On the Hub · Downloads on Model Pulse