sherif1313/Arabic-Qwen3.5-OCR-v4

Partial fine-tune vs Qwen/Qwen3.5-0.8B. Partial change: 66% of the weights changed (attention, embeddings, mlp), in 24 of 24 layers.

Tensors changed: Attention 24/216, Norms 0/129, Embeddings 1/4, MLP 72/124

1 derivatives checked

• mradermacher/Arabic-Qwen3.5-OCR-v4-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse