{"id":19279770,"url":"https://github.com/showlab/visincontext","last_synced_at":"2025-04-22T00:33:01.091Z","repository":{"id":243012304,"uuid":"809865380","full_name":"showlab/VisInContext","owner":"showlab","description":"Official implementation of Leveraging Visual Tokens for Extended Text Contexts in Multi-Modal Learning","archived":false,"fork":false,"pushed_at":"2024-10-30T03:57:48.000Z","size":1034,"stargazers_count":14,"open_issues_count":1,"forks_count":2,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-04-01T17:24:48.337Z","etag":null,"topics":["efficient","in-context-learning","llm","mllm"],"latest_commit_sha":null,"homepage":"https://fingerrec.github.io/visincontext/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/showlab.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2024-06-03T15:41:44.000Z","updated_at":"2024-12-21T13:26:11.000Z","dependencies_parsed_at":"2024-06-06T08:27:58.138Z","dependency_job_id":"9a2009c7-ce79-4810-9f45-9def13f9f66f","html_url":"https://github.com/showlab/VisInContext","commit_stats":null,"previous_names":["showlab/visincontext"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/showlab%2FVisInContext","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/showlab%2FVisInContext/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/showlab%2FVisInContext/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/showlab%2FVisInContext/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/showlab","download_url":"https://codeload.github.com/showlab/VisInContext/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":250158021,"owners_count":21384334,"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":["efficient","in-context-learning","llm","mllm"],"created_at":"2024-11-09T21:16:02.419Z","updated_at":"2025-04-22T00:33:00.604Z","avatar_url":"https://github.com/showlab.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# VisInContext\n\n[Arxiv](https://arxiv.org/abs/2406.02547)\n![](figures/gpu_memory.png)\n\n- VisInContext is a easy way to increase the in-context text length in Multi-modality Learning.\n- This work is also complement with existing works to increase in-context text length like FlashAttn, Memory Transformer.\n\n\n\n## Install\n\n```\npip install -r requirement.txt\n```\n\nFor H100 GPUS, run the following dependencies:\n\n```\npip install -r requirements_h100.txt\n```\n\n\n## Dataset Preparation\nSee [DATASET.md](DATASET.md).\n\n\n## Pre-training\nSee [PRETRAIN.md](PRETRAIN.md).\n\n## Few-shot Evaluation\nSee [Evaluation.md](EVALUATION.md)\n\n\n\n## Citation\n\nIf you find our work helps, please consider cite the following work\n\n```\n@article{wang2024visincontext,\n        title={Leveraging Visual Tokens for Extended Text Contexts in Multi-Modal Learning},\n        author={Wang, Alex Jinpeng and Li, Linjie and Lin, Yiqi and Li, Min  and Wang, Lijuan and Shou, Mike Zheng},\n        journal={NeurIPS},\n        year={2024}\n    }\n\n```\n\n\n\n## Contact\nEmail: awinyimgprocess at gmail dot com\n\n\n## Acknowledgement\nThanks for these good works.\n [Open-flamingo](https://github.com/mlfoundations/open_flamingo), [Open-CLIP](https://github.com/mlfoundations/open_clip) and [WebDataset](https://github.com/webdataset/webdataset).","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fshowlab%2Fvisincontext","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fshowlab%2Fvisincontext","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fshowlab%2Fvisincontext/lists"}