354 MB

Ctrl+K

1 contributor

History: 18 commits

lucasoc

Update README with LightOnOCR-3-4B (0.5232) and Qwen3-VL-8B (0.4872) benchmark results

6ecfe6c verified 22 days ago

configs
feat(config): upload configs/models/qwen2_5_vl_7b.yaml about 2 months ago
docs
docs: add comprehensive failure analysis and error diagnostics for 7B model about 2 months ago
lightonocr_3_4b
Add LightOnOCR-3-4B LoRA adapter and test report (New ICDAR Record 0.5232) 22 days ago
qwen2_5_vl_7b
docs(eval): add 7B evaluation metrics inside subfolder about 2 months ago
qwen3_vl_8b
Add Qwen3-VL-8B LoRA adapter and test report (ICDAR 0.4872) 22 days ago
src
feat: initial release of sci-image-markdown Qwen2.5-VL-3B LoRA adapter and extraction codebase about 2 months ago
.gitattributes

1.57 kB
feat: initial release of sci-image-markdown Qwen2.5-VL-3B LoRA adapter and extraction codebase about 2 months ago
README.md

6.64 kB
Update README with LightOnOCR-3-4B (0.5232) and Qwen3-VL-8B (0.4872) benchmark results 22 days ago
adapter_config.json

1.03 kB
feat: upload qwen2.5-vl-3b native original resolution weights and pt-br model card about 2 months ago
adapter_model.safetensors

14.8 MB
xet

feat: upload qwen2.5-vl-3b native original resolution weights and pt-br model card about 2 months ago
chat_template.jinja

1.02 kB
feat: initial release of sci-image-markdown Qwen2.5-VL-3B LoRA adapter and extraction codebase about 2 months ago
eval_report_7b.json

537 Bytes
docs(eval): add 7B evaluation metrics report (eval_report_7b.json) about 2 months ago
eval_report_orig_res.json

517 Bytes
feat: upload qwen2.5-vl-3b native original resolution weights and pt-br model card about 2 months ago
inference_example.py

2.22 kB
feat: initial release of sci-image-markdown Qwen2.5-VL-3B LoRA adapter and extraction codebase about 2 months ago
processor_config.json

1.26 kB
feat: upload qwen2.5-vl-3b native original resolution weights and pt-br model card about 2 months ago
requirements.txt

494 Bytes
feat: initial release of sci-image-markdown Qwen2.5-VL-3B LoRA adapter and extraction codebase about 2 months ago
tokenizer.json

11.4 MB
xet

feat: initial release of sci-image-markdown Qwen2.5-VL-3B LoRA adapter and extraction codebase about 2 months ago
tokenizer_config.json

786 Bytes
feat: upload qwen2.5-vl-3b native original resolution weights and pt-br model card about 2 months ago
training_args.bin

4.79 kB
xet

feat: upload qwen2.5-vl-3b native original resolution weights and pt-br model card about 2 months ago