ChatDOC/OCRFlux-3B

Full fine-tune vs Qwen/Qwen2.5-VL-3B-Instruct. Fine-tune: 100% of the weights changed, across 36 of 36 layers.

Tensors changed: Norms 80/138, MLP 284/304, Attention 380/380, Embeddings 1/1

3 derivatives checked

• mradermacher/OCRFlux-3B-GGUF: Same weights, converted (fewer layers)
• mradermacher/OCRFlux-3B-i1-GGUF: Quantization (fewer layers)
• ReallyFloppyPenguin/OCRFlux-3B-GGUF: Same weights, converted (fewer layers)

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

On the Hub · Downloads on Model Pulse