{"id":28958823,"url":"https://github.com/togethercomputer/smir","last_synced_at":"2026-03-02T11:33:37.432Z","repository":{"id":275214395,"uuid":"873885499","full_name":"togethercomputer/SMiR","owner":"togethercomputer","description":"synthetic data pipeline for multi-image reasoning","archived":false,"fork":false,"pushed_at":"2025-03-04T21:45:48.000Z","size":984189,"stargazers_count":3,"open_issues_count":0,"forks_count":0,"subscribers_count":4,"default_branch":"main","last_synced_at":"2025-03-04T22:29:55.648Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/togethercomputer.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-10-16T22:18:48.000Z","updated_at":"2025-03-04T21:45:53.000Z","dependencies_parsed_at":null,"dependency_job_id":"c313f71e-b1e6-45ee-a3e5-02207483e52b","html_url":"https://github.com/togethercomputer/SMiR","commit_stats":null,"previous_names":["togethercomputer/smir"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/togethercomputer/SMiR","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/togethercomputer%2FSMiR","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/togethercomputer%2FSMiR/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/togethercomputer%2FSMiR/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/togethercomputer%2FSMiR/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/togethercomputer","download_url":"https://codeload.github.com/togethercomputer/SMiR/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/togethercomputer%2FSMiR/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":261575620,"owners_count":23179552,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-06-23T23:31:35.736Z","updated_at":"2026-03-02T11:33:37.387Z","avatar_url":"https://github.com/togethercomputer.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# SMiR\nSynthetic data pipeline for multi-image reasoning\n\n## Overview\nThis repository contains the official implementation of our paper: [Efficient Synthetic Data Pipeline to Improve Multi-Image Reasoning](https://arxiv.org/abs/2501.03675).\n\n## 🏆 Credits\n\nWe would like to acknowledge the following resources that were instrumental in the development of SMIR:\n\n- [Meta Llama 3.1](https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct): We utilized the Llama 3.1 model as our foundational language model via [\"Together AI\"](https://www.together.ai/models/llama-3-1-70b).\n\n- [SigLIP](https://huggingface.co/timm/ViT-SO400M-14-SigLIP-384): We utilized a SigLIP model as our embedding model from Google.\n\n- [CLIP](https://github.com/facebookresearch/MetaCLIP/blob/main/src/open_clip/model_configs/ViT-H-14-quickgelu.json): We utilized MetaCLIP, Meta's implementation of CLIP, as our embedding model.\n\n- We used training and evaluation code from the following repositories:\n  - [MANTIS: Interleaved Multi-Image Instruction Tuning](https://github.com/TIGER-AI-Lab/Mantis)\n  - [From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline](https://github.com/lmarena/arena-hard-auto)\n\n\u003ca name=\"bibtex\"/\u003e\n\n## 📚 BibTeX\n\n```bibtex\n@misc{li2025smirefficientsyntheticdata,\n      title={SMIR: Efficient Synthetic Data Pipeline To Improve Multi-Image Reasoning}, \n      author={Andrew Li and Rahul Thapa and Rahul Chalamala and Qingyang Wu and Kezhen Chen and James Zou},\n      year={2025},\n      eprint={2501.03675},\n      archivePrefix={arXiv},\n      primaryClass={cs.CV},\n      url={https://arxiv.org/abs/2501.03675}, \n}\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftogethercomputer%2Fsmir","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftogethercomputer%2Fsmir","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftogethercomputer%2Fsmir/lists"}