A collection of benchmarks for evaluating the quality of OCSR models.
🤝 Open to Collab
Hunter Heidenreich
hheiden
AI & ML interests
LLMs and VLMs, OCR and Grounding. AI for Science. Chemical Language Models.
Recent Activity
authored a paper about 10 hours ago
Where to cut, how deep: BPE and Unigram-LM on chemistry SMILES updated a Space about 11 hours ago
hheiden/smiles-subword-vocabularies published a Space about 11 hours ago
hheiden/smiles-subword-vocabulariesOrganizations
None yet
models 0
None public yet
datasets 9
hheiden/mini-proteins-bench
Viewer • Updated • 1 • 90
hheiden/PubChem-124M-SMILES-SELFIES-InChI-IUPAC
Viewer • Updated • 123M • 404 • 8
hheiden/CLEF_OCSR_benchmark
Viewer • Updated • 992 • 47 • 1
hheiden/Colored_Background_OCSR_benchmark
Viewer • Updated • 200 • 27 • 1
hheiden/JPO_OCSR_benchmark
Viewer • Updated • 450 • 27 • 1
hheiden/USPTO_OCSR_benchmark
Viewer • Updated • 5.72k • 28 • 1
hheiden/UOB_OCSR_benchmark
Viewer • Updated • 5.74k • 23 • 1
hheiden/us-congress-bill-policy-115_117
Viewer • Updated • 48k • 67 • 2
hheiden/us-congress-117-bills
Viewer • Updated • 15.2k • 136 • 2