wassname/Open-Assistant
1
0
Fork 0
mirror of https://github.com/wassname/Open-Assistant.git synced 2026-06-27 16:10:30 +08:00
Code Issues Packages Projects Releases Wiki Activity
1,612 Commits 1 Branch 0 Tags
f09eee1ce7265cd617c8d34ef67be0997ff7c8fd
Commit Graph

69 Commits

Author SHA1 Message Date
theblackcat102 670be60ca8 [fix] Fix config typo 2023-01-14 12:17:58 +00:00
theblackcat102 6f6c590e57 [fix] Disable task specific evaluation 2023-01-14 06:47:21 +00:00
theblackcat102 1546111094 [feature] added GSM8k and code refactoring 2023-01-14 06:24:47 +00:00
theblackcat102 3966024871 [fix] Fix summarizer bug and QA typo issue 2023-01-14 05:49:22 +00:00
theblackcat102 9451aff6cc [fix] @ekurtulus major logic bug in summarization 2023-01-14 03:49:19 +00:00
Sotirios Anagnostidis c8f47eef9f precommits 2023-01-11 22:58:17 +01:00
Sotirios Anagnostidis d46ff8c4ee better logging with deepspeed 2023-01-11 22:48:02 +01:00
Sotirios Anagnostidis 6438fdbe2c quantization from #582 2023-01-11 22:44:20 +01:00
Sotirios Anagnostidis 4a3ea0b033 refactoring, now running 2023-01-11 22:42:04 +01:00
ekurtulus 5b77dd2e9f better 2023-01-11 11:37:27 +03:00
mrcabbage972 d95c741ea0 Fixing requirements file 2023-01-10 20:16:02 -05:00
mrcabbage972 67aeed2cd7 Adding override of 32-bit optimization for embedding layer 2023-01-09 23:03:29 -05:00
mrcabbage972 08bdadf222 Adding BNB 8-bit Adam 2023-01-09 22:07:06 -05:00
theblackcat102 a1e1445de9 [fix] evaluation dataset is incorrect in reward-model/trainer.py 2023-01-08 03:42:40 +00:00
theblackcat102 9d05b73efc [fix] syntax error and some typing issue in py38 2023-01-08 02:15:08 +00:00
theblackcat102 116045915e [fix] syntax error and some typing issue in py38 2023-01-08 02:14:49 +00:00
theblackcat102 9eb401c633 [fix] resolve conflict from main 2023-01-08 01:32:39 +00:00
Szymon Ożóg f304921bd5 Added deberta configs 2023-01-07 16:36:55 +01:00
Szymon Ożóg d0942a3256 Added option to use cosine scheduler 2023-01-07 16:36:38 +01:00
theblackcat102 3625f39948 [feature] Add GPTJ synthetic dataset, fix reference removal regex for webgpt 2023-01-07 01:36:27 +00:00
Sotirios Anagnostidis d3952354e2 pre commits 2023-01-06 22:09:24 +01:00
Sotirios Anagnostidis 148244455c refactor 2023-01-06 21:29:38 +01:00
Sotirios Anagnostidis 88ee3b3264 merge deepspeed 2023-01-06 21:28:26 +01:00
Sotirios Anagnostidis f2b125cbe3 merge 2023-01-06 21:24:36 +01:00
Sotirios Anagnostidis 91853753a8 conf 2023-01-06 18:25:20 +01:00
Sotirios Anagnostidis ef02693ac9 quantization 2023-01-06 18:24:28 +01:00
theblackcat102 50e7472ae6 [fix] push fix by linter 2023-01-06 17:14:19 +00:00
theblackcat102 577b14a702 [fix] push fix by linter 2023-01-06 17:11:06 +00:00
theblackcat102 fc6eab9edc [fix] new code complete answer and update readme for clarity 2023-01-06 17:05:47 +00:00
theblackcat102 8e30b419bf [fix] new code complete answer 2023-01-06 16:54:46 +00:00
theblackcat102 b67181776a [feature] add deepspeed, rallio dialogue dataset and codegen parameters 2023-01-06 16:47:58 +00:00
theblackcat102 325c97857c Merge pull request #313 from bth5032/bth5032/78-blackcat-trainer 
Bth5032/78 blackcat trainer
 2023-01-05 10:50:04 +08:00
theblackcat102 93b2be918e Merge pull request #347 from LAION-AI/sft-gptjt-qa-labels 
Sft gptjt qa labels
 2023-01-05 10:49:51 +08:00
Bobak Hashemi 061d621953 removed old precommit pragma requirement 2023-01-04 20:51:19 -05:00
Sotirios Anagnostidis dfaa00dccc gptj 8bit 2023-01-05 00:33:16 +01:00
Bobak Hashemi da79aa04a0 Cleaned up default argument logic. 2023-01-03 21:45:16 -05:00
Bobak Hashemi 4569bcf354 fixed linting 2023-01-03 20:47:33 -05:00
theblackcat102 f7bd22246e [fix] rename old summary human feedback dataset to new one 2023-01-04 01:00:37 +00:00
Sotirios Anagnostidis c20dfaad5b pre-commits 2023-01-03 22:45:34 +01:00
Sotirios Anagnostidis 525e6964e8 requirements 2023-01-03 22:06:59 +01:00
Sotirios Anagnostidis 3a10e9412d Question-Answer special tokens 2023-01-03 22:02:32 +01:00
Bobak Hashemi 45c147362e added precommit hooks and cleaned up configs for rankgen 2023-01-03 01:41:45 -05:00
Bobak Hashemi 568a42066a FP32 Training Works 2023-01-03 00:53:07 -05:00
Sotirios Anagnostidis 675b0866b0 SFT training 2023-01-03 01:31:56 +01:00
Bobak Hashemi 34ab948ade testing rankgen integration into instructor trainer 2023-01-01 23:30:12 -05:00
Gareth Davidson 7000e10bc0 apply pre-commit rules 2023-01-02 00:01:45 +00:00
Yannic Kilcher 4841550cd4 Merge pull request #212 from bitplane/prettier-markdown 
Format markdown with prettier --prose-wrap=always
 2023-01-01 22:11:11 +01:00
Gareth Davidson c3c7a1701a run prettier with new params 2023-01-01 20:57:35 +00:00
Alexander Goryunov e871de693c A typo in import 2023-01-01 21:52:38 +02:00
theblackcat102 8f0028bc44 [fix] Fix provider 2023-01-01 13:28:48 +00:00