typhoon-ai/typhoon-ocr-7b
Full fine-tune vs Qwen/Qwen2.5-VL-7B-Instruct. Fine-tune: 93% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/2, Norms 122/122, MLP 280/280, Attention 324/324, lm_head 1/1
6 derivatives checked
- mradermacher/typhoon-ocr-7b-i1-GGUF: Quantization (fewer layers)
- mradermacher/typhoon-ocr-7b-GGUF: Same weights, converted (fewer layers)
- Adun/typhoon-ocr-7b-v1: LoRA-style
- Adun/typhoon_ocr-7b-v1.2: LoRA-style
- Adun/typhoon_ocr-7B-v1.4: LoRA-style
- Adun/typhoon_ocr-7B-v1.3: LoRA-style
1 other repos hold byte-for-byte identical weight files.