85 Commits

Author SHA1 Message Date
aman-17
796c021ab8 added dotsocr 2025-09-19 13:34:48 -07:00
Jake Poznanski
edd098093b Reverting version changes that broke, vllm 0.10.1 is not good 2025-08-27 18:55:26 +00:00
Jake Poznanski
27792664bf Transformers version bump needed also 2025-08-27 16:35:51 +00:00
Jake Poznanski
03c7479a17 VLLM version bump 2025-08-27 16:33:37 +00:00
Jake Poznanski
dc5c45e144 Deps 2025-08-14 16:10:29 +00:00
Jake Poznanski
7b3b93589d VLLM bump 2025-08-14 16:08:45 +00:00
Jake Poznanski
e664dc5f36 typo 2025-08-05 19:43:11 +00:00
Jake Poznanski
8b8c6bb837 Cleaning up some training requirements installation steps 2025-08-05 19:42:46 +00:00
Jake Poznanski
7dca33db60 Getting things ready for a bit more augmentation 2025-08-05 16:34:46 +00:00
Jake Poznanski
4d773cce8f Adding pytest asyncio 2025-08-04 16:39:27 +00:00
Jake Poznanski
6e8272413c Lint fixes 2025-07-23 03:40:05 +00:00
Jake Poznanski
a4752b5ef9 Merge remote-tracking branch 'origin/main' into jakep/new_trainer 2025-07-23 03:32:49 +00:00
Jake Poznanski
e77bcd20ab Upping vllm versions 2025-07-15 18:43:38 +00:00
Jake Poznanski
5c2d69a3d7 Some cleanup stuff 2025-06-30 21:24:35 +00:00
Jake Poznanski
44cba7911b Bench katex files distributed in installation package now 2025-06-30 17:07:38 +00:00
Jake Poznanski
0ebc35cf1f Basic train config loader for datasets 2025-06-24 22:48:36 +00:00
aman-17
3eda2c04c1 updated vllm to 0.9.1 2025-06-10 16:14:57 -07:00
Jake Poznanski
5c52e016e6 Include cuda 12.8 2025-06-02 22:52:28 +00:00
Jake Poznanski
04dd71c6bf Trying to get onto vllm latest 2025-06-02 18:13:22 +00:00
Jake Poznanski
21d3a3cca1
Update pyproject.toml 2025-05-23 15:14:07 -07:00
Jake Poznanski
1f66b96ffd Adding openai dependecy for benchmarking 2025-04-25 18:18:37 +00:00
Jake Poznanski
cc8e4b1863 Adding native support to convert pngs and jpgs to pdfs so the pipeline can work on them 2025-03-31 10:59:38 -07:00
Jake Poznanski
58276b04cb Mining reading order checkpoint, convert script to use images 2025-03-20 19:49:39 +00:00
Jake Poznanski
4939e41154 Flask based review app first attempt 2025-03-18 16:53:36 +00:00
Chris Wilhelm
7e8492059c wip 2025-03-13 15:31:55 -07:00
Chris Wilhelm
927d7d9117 setup.cfg instead of in pyproject for dep links 2025-03-13 15:31:55 -07:00
Chris Wilhelm
f1524957b1 specify gpu deps in pyproject 2025-03-13 15:31:55 -07:00
Jake Poznanski
95f03e1e42 More small tests 2025-03-13 12:50:52 -07:00
Jake Poznanski
5387a79a2f More tests for olmocrbench 2025-03-12 11:59:11 -07:00
Jake Poznanski
8b3a9e4201 Fixes for multipage runners 2025-03-12 10:29:49 -07:00
Jake Poznanski
4709156ce5 Leaving with some more data, but still cases to investigate 2025-03-10 15:53:01 -07:00
Jake Poznanski
e39c3e4613 New method for comparing equations 2025-03-10 21:47:49 +00:00
Jake Poznanski
af02c63531 Working viewer 2025-02-28 14:00:22 -08:00
Jake Poznanski
143769bcbc
Merge pull request #61 from allenai/kylel/elo
Adds data and scripts for ELO ratings
2025-02-28 10:18:00 -08:00
Jake Poznanski
1b78ec9572 More work on automining 2025-02-28 10:14:47 -08:00
kyleclo
7e434d8466 Merge branch 'main' into kylel/elo 2025-02-28 10:06:40 -08:00
Jake Poznanski
bd08fdb476 fixes missing OSS code for Issue #36 2025-02-26 17:49:04 +00:00
Jake Poznanski
318abf22ad Adding runbench 2025-02-19 19:27:08 +00:00
Jake Poznanski
f50f37efb8 pyproject.toml changes 2025-02-14 22:27:36 +00:00
Jake Poznanski
3ee8b7b45e toml fix 2025-02-14 22:09:29 +00:00
Jake Poznanski
7e02e199ba Adjusting tools to include html templates 2025-02-14 21:42:59 +00:00
Jake Poznanski
c05e01532c Hopefully CI runs now 2025-02-14 20:42:19 +00:00
kyleclo
86b17d0ea3 add boxplot drawing 2025-02-13 19:38:09 -08:00
kyleclo
88c18b3afa human eval data; elo ratings script; dependencies 2025-02-13 16:59:09 -08:00
Jake Poznanski
2ab7cb280c Removing pymupdf 2025-01-30 15:51:54 -08:00
Jake Poznanski
ddeea92591 More dev dependecies 2025-01-30 15:38:29 -08:00
Jake Poznanski
72f4b9a590 Project setup 2025-01-30 15:33:04 -08:00
Jake Poznanski
10094ffc19 Even newer mypy crashes still 2025-01-30 14:32:08 -08:00
Jake Poznanski
7fbbb572ae Remove mypy for now 2025-01-30 13:37:01 -08:00
Jake Poznanski
2c2953329e Fixing most ruff errors 2025-01-29 15:57:26 -08:00