59 Commits

Author SHA1 Message Date
PeterGriffinJin
e98610667a fix typo 2025-05-19 13:30:22 +00:00
PeterGriffinJin
de5c204f17 add autorefine and fix typo 2025-05-19 13:25:54 +00:00
PeterGriffinJin
9db52259b7 fix log 2025-05-16 20:52:52 +00:00
PeterGriffinJin
7dfd7da617 add sok 2025-05-16 20:40:00 +00:00
PeterGriffinJin
59cc844c17 fix index builder key bug 2025-05-16 20:37:44 +00:00
PeterGriffinJin
8ecaa29f43 add logo 2025-05-14 16:02:31 +00:00
PeterGriffinJin
cd02c71fb1 add IKEA 2025-05-13 13:37:45 +00:00
PeterGriffinJin
beff7ecc4f add zerosearch 2025-05-08 12:14:02 +00:00
PeterGriffinJin
1daad32032 update citation 2025-05-05 14:53:05 +00:00
PeterGriffinJin
7d6a15bfc5 remove unuseful file 2025-04-29 16:02:26 +00:00
PeterGriffinJin
bd36c49480 add awesome works 2025-04-28 18:58:25 +00:00
PeterGriffinJin
573ed7e86a add multinode scripts 2025-04-11 13:19:26 +00:00
PeterGriffinJin
f8ee208db1 update readme and add exp logs 2025-04-10 18:45:35 +00:00
PeterGriffinJin
bad47a7e45 fix data dir in multinode readme 2025-04-10 12:31:21 +00:00
PeterGriffinJin
8028a95b30 add multinode example imgs 2025-04-10 12:28:05 +00:00
PeterGriffinJin
a2870cb320 add multinode support 2025-04-10 12:26:43 +00:00
PeterGriffinJin
968c38c38b update v0.1 and v0.2 scripts 2025-04-09 19:38:29 +00:00
PeterGriffinJin
ba78b68eb4 update train script 2025-04-09 19:31:20 +00:00
PeterGriffinJin
8ceb0cd1bb add reranker to readme 2025-04-08 00:39:39 +00:00
PeterGriffinJin
e23b879116 add reranker 2025-04-08 00:37:39 +00:00
PeterGriffinJin
04d4152575 add indexing for ANN and bm25 2025-04-07 18:35:41 +00:00
PeterGriffinJin
a7fa1febff fix typos 2025-04-07 18:30:08 +00:00
PeterGriffinJin
bfc61e90fa update features 2025-04-07 18:28:05 +00:00
PeterGriffinJin
5eccb5fa14 add example scripts for ANN and BM25 2025-04-07 18:27:55 +00:00
PeterGriffinJin
ba152349fd add local sparse retriever, ann dense retriever and online search engine 2025-04-07 18:20:43 +00:00
PeterGriffinJin
0b26e614f7 fix proto bug 2025-04-04 02:54:21 +00:00
PeterGriffinJin
7530318919 fix test dataloader shuffle bug 2025-04-02 22:23:11 +00:00
PeterGriffinJin
716cd73977 add more data processing codes 2025-03-31 12:58:04 +00:00
PeterGriffinJin
95d16f4548 fix potential float bug 2025-03-27 16:21:04 +00:00
PeterGriffinJin
f5204213d3 clean up retrieval cache 2025-03-23 14:33:14 +00:00
PeterGriffinJin
6272082a64 fix action status 2025-03-22 14:49:23 +00:00
PeterGriffinJin
4936a3115e add code for inference 2025-03-21 20:27:54 +00:00
PeterGriffinJin
d874947732 fix turns_stats logging bug 2025-03-21 14:58:42 +00:00
PeterGriffinJin
83d10313be add action status 2025-03-19 22:19:27 +00:00
PeterGriffinJin
9ec2fa9892 fix grpo id bug 2025-03-19 18:59:19 +00:00
PeterGriffinJin
8c7f04ca45 response length include retrieval info 2025-03-19 00:36:21 +00:00
Bowen Jin
50cedb2c00 Merge pull request #21 from xiaobo-yang/yxb/fix-info-mask-bugs
Fix bugs related to loss mask, meta info, and response length
2025-03-18 19:33:50 -05:00
PeterGriffinJin
8501d1cdf7 add citation 2025-03-18 22:27:00 +00:00
PeterGriffinJin
4b3c09451a fix kl loss issue 2025-03-18 20:07:47 +00:00
PeterGriffinJin
e85506f143 remove unnecessary codes 2025-03-17 16:08:33 +00:00
xiaobo-yang
32719b5119 Fix bugs related to loss mask, meta info, and response length
1. Construct the loss mask immediately after obtaining the observation to prevent encoding misalignment when converting back to tokens after text transformation.
2. Follow up on meta info to ensure that the test batch can apply do sample.
3. Remove the recording of info information for response length.
2025-03-14 14:25:40 +08:00
PeterGriffinJin
118c6e7361 fix reward bug 2025-03-13 19:18:56 +00:00
PeterGriffinJin
ff85cb7f1e fix file name bug 2025-03-13 14:42:21 +00:00
PeterGriffinJin
7ffeeaba0f modify readme 2025-03-13 14:00:41 +00:00
PeterGriffinJin
66cd336580 fix wandb link bug 2025-03-13 13:59:55 +00:00
PeterGriffinJin
fb9940972c fix typo 2025-03-13 13:58:23 +00:00
PeterGriffinJin
584ce9deb5 add paper scripts 2025-03-13 13:57:47 +00:00
PeterGriffinJin
0ecaf6da76 add ckpt link 2025-03-12 15:33:00 +00:00
PeterGriffinJin
c4e0269cfc add grpo script 2025-03-12 15:16:03 +00:00
PeterGriffinJin
1bd9cf1749 add citation 2025-03-04 19:42:53 +00:00