Materials Welcome to IBM’s multi-modal foundation model for materials, FM4M, designed to support and advance research in materials science and chemistry. Feature Extraction • Updated Jul 2, 2025 • 159 • 37 Feature Extraction • 0.4B • Updated Oct 13, 2025 • 14.1k • • 11 Feature Extraction • Updated Oct 13, 2025 • 39 • 4 Feature Extraction • Updated Dec 5, 2024 • 9 • 8
✨ Highlights Unitxt ⚡ 2 Paper • 2308.16884 • Published Aug 31, 2023 • 11 BenchBench Leaderboad 🏋 8 Compare benchmarks for language models
Genie: Wishes datasets Wishes datasets created by Genie Viewer • Updated Feb 5, 2024 • 10.8k • 25 • 1 Viewer • Updated Feb 5, 2024 • 39.3k • 39 Viewer • Updated Feb 5, 2024 • 10k • 18 • 1 Viewer • Updated Feb 5, 2024 • 4.35k • 24
Paraphrase and perturbation question-answering robustness Datasets from "A Novel Metric for Measuring the Robustness of Large Language Models in Non-adversarial Scenarios" (https://arxiv.org/abs/2408.01963) Viewer • Updated Aug 19, 2024 • 29.4k • 9 Viewer • Updated Aug 19, 2024 • 21.8k • 21 • 2 Viewer • Updated Aug 19, 2024 • 204k • 13
BioMed A suite of open-source biomedical foundation models. https://research.ibm.com/projects/biomedical-foundation-models Biomed.sm.mv Te 84m 👁 4 Prediction task tests for biomed-multi-view models Biomed-multi-alignment unified demo with PPI and TDI examples 🐁 3 Demo for MAMMAL approch on multiple domains 0.5B • Updated Dec 19, 2024 • 445 • 51 Updated Feb 24 • 75 • 19
Biomed-multi-alignment unified demo with PPI and TDI examples 🐁 3 Demo for MAMMAL approch on multiple domains
Power-LM Dense & MoE LLMs trained with power learning rate scheduler. Paper • 2408.13359 • Published Aug 23, 2024 • 23 Text Generation • 4B • Updated Sep 16, 2024 • 185k • 21 Text Generation • 3B • Updated Sep 24, 2024 • 1.58M • 21
🔬 Research Paper • 2401.14019 • Published Jan 25, 2024 • 23 Paper • 2308.16884 • Published Aug 31, 2023 • 11 Paper • 2401.14367 • Published Jan 25, 2024 • 8 Image Feature Extraction • Updated Sep 5, 2025 • 339 • 84
Materials Welcome to IBM’s multi-modal foundation model for materials, FM4M, designed to support and advance research in materials science and chemistry. Feature Extraction • Updated Jul 2, 2025 • 159 • 37 Feature Extraction • 0.4B • Updated Oct 13, 2025 • 14.1k • • 11 Feature Extraction • Updated Oct 13, 2025 • 39 • 4 Feature Extraction • Updated Dec 5, 2024 • 9 • 8
BioMed A suite of open-source biomedical foundation models. https://research.ibm.com/projects/biomedical-foundation-models Biomed.sm.mv Te 84m 👁 4 Prediction task tests for biomed-multi-view models Biomed-multi-alignment unified demo with PPI and TDI examples 🐁 3 Demo for MAMMAL approch on multiple domains 0.5B • Updated Dec 19, 2024 • 445 • 51 Updated Feb 24 • 75 • 19
Biomed-multi-alignment unified demo with PPI and TDI examples 🐁 3 Demo for MAMMAL approch on multiple domains
✨ Highlights Unitxt ⚡ 2 Paper • 2308.16884 • Published Aug 31, 2023 • 11 BenchBench Leaderboad 🏋 8 Compare benchmarks for language models
Power-LM Dense & MoE LLMs trained with power learning rate scheduler. Paper • 2408.13359 • Published Aug 23, 2024 • 23 Text Generation • 4B • Updated Sep 16, 2024 • 185k • 21 Text Generation • 3B • Updated Sep 24, 2024 • 1.58M • 21
Genie: Wishes datasets Wishes datasets created by Genie Viewer • Updated Feb 5, 2024 • 10.8k • 25 • 1 Viewer • Updated Feb 5, 2024 • 39.3k • 39 Viewer • Updated Feb 5, 2024 • 10k • 18 • 1 Viewer • Updated Feb 5, 2024 • 4.35k • 24
🔬 Research Paper • 2401.14019 • Published Jan 25, 2024 • 23 Paper • 2308.16884 • Published Aug 31, 2023 • 11 Paper • 2401.14367 • Published Jan 25, 2024 • 8 Image Feature Extraction • Updated Sep 5, 2025 • 339 • 84
Paraphrase and perturbation question-answering robustness Datasets from "A Novel Metric for Measuring the Robustness of Large Language Models in Non-adversarial Scenarios" (https://arxiv.org/abs/2408.01963) Viewer • Updated Aug 19, 2024 • 29.4k • 9 Viewer • Updated Aug 19, 2024 • 21.8k • 21 • 2 Viewer • Updated Aug 19, 2024 • 204k • 13