From 377a1270234bbc77d5406d545610a5c4f08e1be4 Mon Sep 17 00:00:00 2001 From: Vimal_Shady <144231334+Vimal-Shady@users.noreply.github.com> Date: Wed, 6 Aug 2025 14:10:28 +0530 Subject: [PATCH 1/5] Fix Broken Link in README --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index fc7e0be06..a8e31c299 100644 --- a/README.md +++ b/README.md @@ -37,7 +37,7 @@ Transform Optimize   - + Get started From caa70085467193f2d408495536f3f6b1d5ba2f0e Mon Sep 17 00:00:00 2001 From: Vimal_Shady <144231334+Vimal-Shady@users.noreply.github.com> Date: Wed, 6 Aug 2025 21:57:10 +0530 Subject: [PATCH 2/5] Added Markdown Link Checker Workflow --- .github/markdown-links-config.json | 12 ++++++++++++ .github/workflows/ci-check-md-links.yml | 21 +++++++++++++++++++++ 2 files changed, 33 insertions(+) create mode 100644 .github/markdown-links-config.json create mode 100644 .github/workflows/ci-check-md-links.yml diff --git a/.github/markdown-links-config.json b/.github/markdown-links-config.json new file mode 100644 index 000000000..b6bf72eb1 --- /dev/null +++ b/.github/markdown-links-config.json @@ -0,0 +1,12 @@ +{ + "ignorePatterns": [ + { + "pattern": "^http://localhost" + }, + { + "pattern": "^https://example.com" + } + ], + "timeout": "10", + "retryCount": 2 +} diff --git a/.github/workflows/ci-check-md-links.yml b/.github/workflows/ci-check-md-links.yml new file mode 100644 index 000000000..72ffb61ba --- /dev/null +++ b/.github/workflows/ci-check-md-links.yml @@ -0,0 +1,21 @@ +name: Check Markdown links +# https://github.com/gaurav-nelson/github-action-markdown-link-check + +on: + push: + branches: [main, "release/*"] + pull_request: + branches: [main, "release/*"] + types: [opened, reopened, ready_for_review, synchronize] + paths: + - ".github/workflows/ci-check-md-links.yml" + - ".github/markdown-links-config.json" + - "**/*.md" + +jobs: + check-md-links: + uses: Lightning-AI/utilities/.github/workflows/check-md-links.yml@main + with: + config-file: ".github/markdown-links-config.json" + base-branch: "main" + force-check-all: "yes" From d8c5adbcf6a070187b600418412130a875a17d62 Mon Sep 17 00:00:00 2001 From: Deependu Jha Date: Thu, 7 Aug 2025 13:33:09 +0530 Subject: [PATCH 3/5] update --- .github/markdown-links-config.json | 26 +++++++++++++++++++++---- .github/workflows/ci-check-md-links.yml | 21 -------------------- .github/workflows/ci-checks.yml | 7 +++++++ 3 files changed, 29 insertions(+), 25 deletions(-) delete mode 100644 .github/workflows/ci-check-md-links.yml diff --git a/.github/markdown-links-config.json b/.github/markdown-links-config.json index b6bf72eb1..50dea4c54 100644 --- a/.github/markdown-links-config.json +++ b/.github/markdown-links-config.json @@ -1,12 +1,30 @@ { "ignorePatterns": [ { - "pattern": "^http://localhost" + "pattern": "^https://github.com/Lightning-AI/litData/pull/" }, { - "pattern": "^https://example.com" + "pattern": "^https://dev.azure.com/Lightning-AI/lightning/_apis/build/status" + }, + { + "pattern": "^https://codecov.io/gh/Lightning-AI/litData/graph/badge.svg" + } + ], + "httpHeaders": [ + { + "urls": [ + "https://github.com/", + "https://guides.github.com/", + "https://help.github.com/", + "https://docs.github.com/" + ], + "headers": { + "Accept-Encoding": "zstd, br, gzip, deflate" + } } ], - "timeout": "10", - "retryCount": 2 + "timeout": "20s", + "retryOn429": true, + "retryCount": 5, + "fallbackRetryDelay": "20s" } diff --git a/.github/workflows/ci-check-md-links.yml b/.github/workflows/ci-check-md-links.yml deleted file mode 100644 index 72ffb61ba..000000000 --- a/.github/workflows/ci-check-md-links.yml +++ /dev/null @@ -1,21 +0,0 @@ -name: Check Markdown links -# https://github.com/gaurav-nelson/github-action-markdown-link-check - -on: - push: - branches: [main, "release/*"] - pull_request: - branches: [main, "release/*"] - types: [opened, reopened, ready_for_review, synchronize] - paths: - - ".github/workflows/ci-check-md-links.yml" - - ".github/markdown-links-config.json" - - "**/*.md" - -jobs: - check-md-links: - uses: Lightning-AI/utilities/.github/workflows/check-md-links.yml@main - with: - config-file: ".github/markdown-links-config.json" - base-branch: "main" - force-check-all: "yes" diff --git a/.github/workflows/ci-checks.yml b/.github/workflows/ci-checks.yml index 7552db466..4fe3fe837 100644 --- a/.github/workflows/ci-checks.yml +++ b/.github/workflows/ci-checks.yml @@ -37,3 +37,10 @@ jobs: uses: Lightning-AI/utilities/.github/workflows/check-docs.yml@main with: requirements-file: "requirements/docs.txt" + + check-md-links: + uses: Lightning-AI/utilities/.github/workflows/check-md-links.yml@main + with: + config-file: ".github/markdown-links-config.json" + base-branch: "main" + force-check-all: "yes" From f5f8b9af1d98ce09e0bb1839f0782b467d3b63fd Mon Sep 17 00:00:00 2001 From: Deependu Jha Date: Thu, 7 Aug 2025 13:44:28 +0530 Subject: [PATCH 4/5] update --- README.md | 2 +- examples/multi_modal/README.md | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index aebe2058a..422f003b8 100644 --- a/README.md +++ b/README.md @@ -571,7 +571,7 @@ Stream data during long training, if interrupted, pick up right where you left o LitData provides a stateful `Streaming DataLoader` e.g. you can `pause` and `resume` your training whenever you want. -Info: The `Streaming DataLoader` was used by [Lit-GPT](https://github.com/Lightning-AI/lit-gpt/blob/main/pretrain/tinyllama.py) to pretrain LLMs. Restarting from an older checkpoint was critical to get to pretrain the full model due to several failures (network, CUDA Errors, etc..). +Info: The `Streaming DataLoader` was used by [Lit-GPT](https://github.com/Lightning-AI/litgpt/blob/main/tutorials/pretrain_tinyllama.md) to pretrain LLMs. Restarting from an older checkpoint was critical to get to pretrain the full model due to several failures (network, CUDA Errors, etc..). ```python import os diff --git a/examples/multi_modal/README.md b/examples/multi_modal/README.md index 97c2999d4..d192b2bda 100644 --- a/examples/multi_modal/README.md +++ b/examples/multi_modal/README.md @@ -126,7 +126,7 @@ pip install -r requirements.txt ## License -This project is licensed under the APACHE 2.0 License. See the [LICENSE](LICENSE) file for details. +This project is licensed under the [APACHE 2.0 License](https://github.com/Lightning-AI/litData/blob/main/LICENSE). ______________________________________________________________________ From 761f16e3f6e319f3103cfae247a9e2eae362e0b9 Mon Sep 17 00:00:00 2001 From: Deependu Date: Thu, 7 Aug 2025 14:12:52 +0530 Subject: [PATCH 5/5] Update .github/markdown-links-config.json Co-authored-by: Bhimraj Yadav --- .github/markdown-links-config.json | 3 --- 1 file changed, 3 deletions(-) diff --git a/.github/markdown-links-config.json b/.github/markdown-links-config.json index 50dea4c54..76bbc794a 100644 --- a/.github/markdown-links-config.json +++ b/.github/markdown-links-config.json @@ -3,9 +3,6 @@ { "pattern": "^https://github.com/Lightning-AI/litData/pull/" }, - { - "pattern": "^https://dev.azure.com/Lightning-AI/lightning/_apis/build/status" - }, { "pattern": "^https://codecov.io/gh/Lightning-AI/litData/graph/badge.svg" }