Skip to content

Actions: huggingface/trl

Actions

Build documentation

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build_documentation.yml
739 workflow runs
739 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

fix: typos in documentation files (#2804) Build documentation #1120: Commit 55e680e pushed by qgallouedec
February 8, 2025 19:46 3m 34s main
main
February 8, 2025 19:46 3m 34s
⛰️ Reduce peak vram consumption with efficient selective log_softmax … Build documentation #1119: Commit 09eefa7 pushed by qgallouedec
February 7, 2025 23:59 3m 28s main
main
February 7, 2025 23:59 3m 28s
➖ Fix GRPO example in README (#2800) Build documentation #1118: Commit 7fdb69a pushed by qgallouedec
February 7, 2025 23:29 3m 45s main
main
February 7, 2025 23:29 3m 45s
🔬 SFT simplification (#2405) Build documentation #1117: Commit 5b9236d pushed by qgallouedec
February 7, 2025 23:21 3m 28s main
main
February 7, 2025 23:21 3m 28s
📠 Log completions for GRPO (#2772) Build documentation #1116: Commit 82d12eb pushed by qgallouedec
February 7, 2025 11:42 3m 31s main
main
February 7, 2025 11:42 3m 31s
🎯 [SFT] add token accuracy metric (#2597) Build documentation #1115: Commit 84d73fd pushed by qgallouedec
February 7, 2025 10:09 3m 34s main
main
February 7, 2025 10:09 3m 34s
🆚 Distinguish padding and eos when they differ (#2793) Build documentation #1114: Commit 2241f17 pushed by qgallouedec
February 7, 2025 10:08 3m 22s main
main
February 7, 2025 10:08 3m 22s
💡 Add 'Post training an LLM for reasoning with GRPO in TRL' tutorial … Build documentation #1113: Commit 724acb9 pushed by qgallouedec
February 6, 2025 17:28 3m 53s main
main
February 6, 2025 17:28 3m 53s
Revert "Before the first training step, the model has no optimizer: f… Build documentation #1112: Commit 7134a1e pushed by qgallouedec
February 6, 2025 17:20 3m 48s main
main
February 6, 2025 17:20 3m 48s
Before the first training step, the model has no optimizer: fix ds3 Build documentation #1111: Commit bf6e7ed pushed by qgallouedec
February 6, 2025 17:19 3m 53s main
main
February 6, 2025 17:19 3m 53s
🙃 Fix reward function in GRPO example (#2777) Build documentation #1110: Commit e95f9fb pushed by qgallouedec
February 6, 2025 08:51 3m 33s main
main
February 6, 2025 08:51 3m 33s
💡 GRPO vram-efficiency improvement; only compute relevant logprobs (… Build documentation #1109: Commit a85768f pushed by qgallouedec
February 6, 2025 07:52 3m 19s main
main
February 6, 2025 07:52 3m 19s
↔️ GRPO: Set max_model_len when initializing vLLM instance (#2728) Build documentation #1108: Commit 78c5ce2 pushed by qgallouedec
February 5, 2025 23:12 3m 26s main
main
February 5, 2025 23:12 3m 26s
🚧 Add Optional ZeRO-3 Weight Gathering for GRPO in Sequence Generatio… Build documentation #1107: Commit af4ad47 pushed by qgallouedec
February 4, 2025 22:24 3m 44s main
main
February 4, 2025 22:24 3m 44s
🔁 🦈 Support iterative GRPO (#2700) Build documentation #1106: Commit b2ae999 pushed by qgallouedec
February 4, 2025 22:10 3m 28s main
main
February 4, 2025 22:10 3m 28s
🤖 Properly unwrap torch.compile-ed models in GRPO (#2750) Build documentation #1105: Commit bd946f9 pushed by qgallouedec
February 4, 2025 21:22 3m 59s main
main
February 4, 2025 21:22 3m 59s
🔎 Add missing script argument in PPO documentation (#2720) Build documentation #1104: Commit f42e34e pushed by qgallouedec
February 4, 2025 20:53 3m 59s main
main
February 4, 2025 20:53 3m 59s
📖 Clarification max len in Reward documentation (#2740) Build documentation #1103: Commit 338fbd5 pushed by qgallouedec
February 4, 2025 20:16 4m 17s main
main
February 4, 2025 20:16 4m 17s
📐 Add vLLM dtype configuration for GRPO trainer (#2738) Build documentation #1102: Commit 32f8fa8 pushed by qgallouedec
February 4, 2025 20:11 3m 56s main
main
February 4, 2025 20:11 3m 56s
📌 vLLM >= 0.7.1 for device fix (#2766) Build documentation #1101: Commit 1a22764 pushed by qgallouedec
February 4, 2025 19:12 4m 9s main
main
February 4, 2025 19:12 4m 9s
💔 Decouple loss computing and generation in GRPO (#2762) Build documentation #1100: Commit 1f344c9 pushed by qgallouedec
February 4, 2025 12:21 3m 33s main
main
February 4, 2025 12:21 3m 33s
🔂 Use vLLM prefix caching for speedup (#2757) Build documentation #1099: Commit 85121fc pushed by qgallouedec
February 4, 2025 10:20 3m 44s main
main
February 4, 2025 10:20 3m 44s
⚠️ Fix attention masking in GRPO (#2708) Build documentation #1098: Commit bbdd6db pushed by qgallouedec
February 2, 2025 19:44 3m 25s main
main
February 2, 2025 19:44 3m 25s
docs: Fix typos in alias descriptions (#2729) Build documentation #1097: Commit 6e088d1 pushed by qgallouedec
February 2, 2025 10:59 3m 19s main
main
February 2, 2025 10:59 3m 19s
fix: Fix typo in filename in ultrafeedback-prompt.py (#2716) Build documentation #1096: Commit a325a0e pushed by qgallouedec
February 1, 2025 13:53 3m 20s main
main
February 1, 2025 13:53 3m 20s