Skip to content

Actions: huggingface/trl

Actions

Build PR Documentation

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build_pr_documentation.yml
3,714 workflow runs
3,714 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Fix length bias for Dr GRPO Build PR Documentation #7054: Pull request #3138 synchronize by idoru
March 23, 2025 22:51 Action required idoru:dr-grpo-fix-length-bias
idoru:dr-grpo-fix-length-bias
March 23, 2025 22:51 Action required
📊 Fix clip_ratio logging and better document logged values Build PR Documentation #7053: Pull request #3145 synchronize by qgallouedec
March 23, 2025 20:50 3m 33s fix-is_clipped-for-logging
fix-is_clipped-for-logging
March 23, 2025 20:50 3m 33s
feat: Add Interleaved Trainer implementation Build PR Documentation #7052: Pull request #3107 synchronize by ucalyptus2
March 23, 2025 20:42 Action required ucalyptus2:main
ucalyptus2:main
March 23, 2025 20:42 Action required
📊 Fix clip_ratio logging and better document logged values Build PR Documentation #7051: Pull request #3145 synchronize by qgallouedec
March 23, 2025 19:18 3m 48s fix-is_clipped-for-logging
fix-is_clipped-for-logging
March 23, 2025 19:18 3m 48s
📊 Fix clip_ratio logging and better document logged values Build PR Documentation #7050: Pull request #3145 opened by qgallouedec
March 23, 2025 19:16 1m 53s fix-is_clipped-for-logging
fix-is_clipped-for-logging
March 23, 2025 19:16 1m 53s
Fix length bias for Dr GRPO Build PR Documentation #7048: Pull request #3138 synchronize by idoru
March 23, 2025 05:25 Action required idoru:dr-grpo-fix-length-bias
idoru:dr-grpo-fix-length-bias
March 23, 2025 05:25 Action required
Add GRPO/ Online DPO support for quantitative models when use vllm as infer backbone. Build PR Documentation #7047: Pull request #3133 synchronize by maoulee
March 23, 2025 04:58 Action required maoulee:main
maoulee:main
March 23, 2025 04:58 Action required
Fix length bias for Dr GRPO Build PR Documentation #7046: Pull request #3138 opened by idoru
March 23, 2025 02:31 Action required idoru:dr-grpo-fix-length-bias
idoru:dr-grpo-fix-length-bias
March 23, 2025 02:31 Action required
Release: v0.16 Build PR Documentation #7044: Pull request #3137 synchronize by qgallouedec
March 22, 2025 21:03 3m 36s release-v0.16
release-v0.16
March 22, 2025 21:03 3m 36s
Release: v0.16 Build PR Documentation #7043: Pull request #3137 opened by qgallouedec
March 22, 2025 21:02 42s release-v0.16
release-v0.16
March 22, 2025 21:02 42s
☎️ Documentation for disable gathering of model weights for generation in DeepSpeed ZeRO-3 Build PR Documentation #7042: Pull request #3136 synchronize by qgallouedec
March 22, 2025 20:10 3m 34s doc-no-gathering-z3-grpo
doc-no-gathering-z3-grpo
March 22, 2025 20:10 3m 34s
☎️ Documentation for disable gathering of model weights for generation in DeepSpeed ZeRO-3 Build PR Documentation #7041: Pull request #3136 opened by qgallouedec
March 22, 2025 20:09 29s doc-no-gathering-z3-grpo
doc-no-gathering-z3-grpo
March 22, 2025 20:09 29s
⚖️ Add option not to scale rewards (Dr. GRPO) Build PR Documentation #7040: Pull request #3135 synchronize by qgallouedec
March 22, 2025 19:57 3m 24s dr-grpo
dr-grpo
March 22, 2025 19:57 3m 24s
⚖️ Add option not to scale rewards (Dr. GRPO) Build PR Documentation #7039: Pull request #3135 opened by qgallouedec
March 22, 2025 19:11 3m 38s dr-grpo
dr-grpo
March 22, 2025 19:11 3m 38s
🐍 Support Python 3.13 Build PR Documentation #7038: Pull request #2593 synchronize by qgallouedec
March 22, 2025 18:41 3m 29s python-3.13
python-3.13
March 22, 2025 18:41 3m 29s
⚡ Pack 300 times faster, truncate 100 times faster Build PR Documentation #7037: Pull request #3009 synchronize by qgallouedec
March 22, 2025 18:32 3m 49s mariosasko:fast-pack-truncate
mariosasko:fast-pack-truncate
March 22, 2025 18:32 3m 49s
⚡ Pack 300 times faster, truncate 100 times faster Build PR Documentation #7036: Pull request #3009 synchronize by qgallouedec
March 22, 2025 18:24 3m 36s mariosasko:fast-pack-truncate
mariosasko:fast-pack-truncate
March 22, 2025 18:24 3m 36s
Extend BCO Trainer dataset format support Build PR Documentation #7035: Pull request #3134 opened by reihig-ut
March 22, 2025 14:20 Action required reihig-ut:dataset_format_for_bco
reihig-ut:dataset_format_for_bco
March 22, 2025 14:20 Action required
Add GRPO/ Online DPO support for quantitative models when use vllm as infer backbone. Build PR Documentation #7034: Pull request #3133 opened by maoulee
March 22, 2025 05:53 Action required maoulee:main
maoulee:main
March 22, 2025 05:53 Action required
🚀 Scaling GRPO to 70B+ Models and Multi-Node Training with vLLM Server & NCCL Communication Build PR Documentation #7032: Pull request #3094 synchronize by qgallouedec
March 21, 2025 18:32 3m 58s binary-husky:main
binary-husky:main
March 21, 2025 18:32 3m 58s
🚀 Scaling GRPO to 70B+ Models and Multi-Node Training with vLLM Server & NCCL Communication Build PR Documentation #7031: Pull request #3094 synchronize by qgallouedec
March 21, 2025 18:31 1m 2s binary-husky:main
binary-husky:main
March 21, 2025 18:31 1m 2s
🚀 Scaling GRPO to 70B+ Models and Multi-Node Training with vLLM Server & NCCL Communication Build PR Documentation #7029: Pull request #3094 synchronize by qgallouedec
March 21, 2025 16:55 3m 58s binary-husky:main
binary-husky:main
March 21, 2025 16:55 3m 58s
💎 Gemma 3 VLM SFT example script for single-image and multi-image Build PR Documentation #7028: Pull request #3131 synchronize by sergiopaniego
March 21, 2025 16:38 4m 13s sergiopaniego:sft-vlm-gemma3
sergiopaniego:sft-vlm-gemma3
March 21, 2025 16:38 4m 13s
💎 Gemma 3 VLM SFT example script for single-image and multi-image Build PR Documentation #7027: Pull request #3131 synchronize by sergiopaniego
March 21, 2025 16:34 3m 45s sergiopaniego:sft-vlm-gemma3
sergiopaniego:sft-vlm-gemma3
March 21, 2025 16:34 3m 45s
💎 Gemma 3 VLM SFT example script for single-image and multi-image Build PR Documentation #7026: Pull request #3131 opened by sergiopaniego
March 21, 2025 15:48 4m 13s sergiopaniego:sft-vlm-gemma3
sergiopaniego:sft-vlm-gemma3
March 21, 2025 15:48 4m 13s