Archives
/
reflexion-human-eval
mirror of https://github.com/GammaTauAI/reflexion-human-eval
2
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Commit Graph

  • d15acda1c8 User change main Noah Shinn 2023-11-25 17:05:42 -0800
  • 612e616603 Update instructions Noah Shinn 2023-10-11 22:02:03 -0700
  • 7fd837de07 Eddie README EdwardBerman 2023-09-29 15:59:27 -0400
  • 47b2a0478a update Noah Shinn 2023-09-26 00:54:10 -0700
  • 49485efc8f undo cassanof 2023-08-28 23:00:09 -0700
  • 9c8dc6617e decent few-shot cassanof 2023-08-28 22:40:21 -0700
  • 7247f0c306 fix cassanof 2023-08-28 21:56:07 -0700
  • 468ed1f8bf exec cassanof 2023-08-28 21:53:01 -0700
  • cc6b8f1192 rstrip codellama cassanof 2023-08-28 16:25:21 -0700
  • f748264b35 allow to get smol boi or big boi cassanof 2023-08-28 15:56:24 -0700
  • 0a9ebab46b big boi llama cassanof 2023-08-28 15:54:05 -0700
  • 45c7f2c50e fix cassanof 2023-08-28 15:52:10 -0700
  • 872e56c928 a cassanof 2023-08-28 15:49:52 -0700
  • 1f62bab132 fix parse cassanof 2023-08-28 15:49:05 -0700
  • 1d70a0026f fix cassanof 2023-08-28 15:35:24 -0700
  • 3dec2edc92 out extract cassanof 2023-08-28 15:31:07 -0700
  • 3b2de1a67e fix cassanof 2023-08-28 15:27:37 -0700
  • f7d1613f8e tensor cassanof 2023-08-28 15:09:58 -0700
  • 0365be2c6e factory cassanof 2023-08-28 15:00:28 -0700
  • afcfd427a2 code llaam cassanof 2023-08-28 14:58:53 -0700
  • e5cdf8c260 codellama cassanof 2023-08-28 14:58:33 -0700
  • abd6ed5a3d woops cassanof 2023-08-28 14:46:31 -0700
  • f799068dec fix eos cassanof 2023-08-28 14:44:07 -0700
  • be7fb52cf7 cahce cassanof 2023-08-28 14:41:33 -0700
  • 3fec014d0a tok cassanof 2023-08-28 14:40:11 -0700
  • 7470891d85 no pipeline cassanof 2023-08-28 14:38:47 -0700
  • f42e651445 better design cassanof 2023-08-28 14:22:45 -0700
  • c3cfcb8863 upd cassanof 2023-08-28 14:13:06 -0700
  • 838ec56d7f . Noah Shinn 2023-08-24 11:00:28 -0700
  • cefdb0ed53 Run Hotpot experiments hotpot-enhancement Beck LaBash 2023-08-24 09:58:51 -0700
  • 65001352fd fix chat completion Noah Shinn 2023-08-05 00:05:33 -0700
  • cf0e1c1a4b fix chat completion Noah Shinn 2023-08-04 23:29:56 -0700
  • 6a295d2083 resume with success count Noah Shinn 2023-08-04 21:26:46 -0700
  • 7f591653c4 aa cassanof 2023-08-04 21:00:59 -0700
  • 7f7a4c586c bleh cassanof 2023-08-04 20:42:46 -0700
  • 8fdf5a9d2a starchat formatting Noah Shinn 2023-08-04 20:33:28 -0700
  • 59db1fb92a fix wrong condition Noah Shinn 2023-08-04 00:02:40 -0700
  • 7e8b29a5bb remove last of challenge set for alfworld Noah Shinn 2023-08-03 23:41:10 -0700
  • be94bc418b fix code block instruction always python Noah Shinn 2023-08-03 23:40:39 -0700
  • 510ed0008e fixes #19 Noah Shinn 2023-08-03 23:11:19 -0700
  • 59c84d9854 add code block instruction Noah Shinn 2023-08-03 23:01:56 -0700
  • f2720b347a
         Implement AnyOpenAILLM for use across completion and chat endpoints (#20) Beck LaBash 2023-08-03 23:01:23 -0700
  • b0fc179059 Implement AnyOpenAILLM for use across completion and chat endpoints Beck LaBash 2023-08-03 23:00:19 -0700
  • d0b997e181 add parser Noah Shinn 2023-08-03 22:54:32 -0700
  • 851b46779c parse code blocks Noah Shinn 2023-08-03 22:51:08 -0700
  • e085b08de5 fix literal import Noah Shinn 2023-08-03 22:33:59 -0700
  • f5ac5200e9 requirements for alfworld Noah Shinn 2023-08-03 22:15:37 -0700
  • 8a2aa8afb8 alfworld chat Noah Shinn 2023-08-03 22:07:12 -0700
  • ff7bbeb22b better messages Noah Shinn 2023-08-03 20:53:45 -0700
  • e5c64d96f0 better messages Noah Shinn 2023-08-03 20:51:19 -0700
  • af69490a59 scripts starchat cassanof 2023-08-02 21:53:27 -0700
  • 8a03029c34 todo cassanof 2023-08-02 21:51:12 -0700
  • a8e13b1b0f fix simple cassanof 2023-08-02 21:38:50 -0700
  • 0e45c6a115
         Merge pull request #15 from noahshinn024/starchat Federico Cassano 2023-08-02 21:23:58 -0700
  • 021afedc65
         Update prompts.py liwy 2023-08-02 15:48:24 +0800
  • f63cc5e4e9
         Merge 50bfc5ada4 into f27481d8a3 epinnock 2023-06-24 19:56:24 -0700
  • 50bfc5ada4 commit for locallm Ejiro Pinnock 2023-06-25 02:52:09 +0000
  • 807a06578c todo file Noah Shinn 2023-06-20 23:44:50 -0700
  • 1c7367fb1c Start code parsing and instruction Noah Shinn 2023-06-20 23:43:28 -0700
  • fc411f1d49 simple strategy now runs on local llm Ejiro Pinnock 2023-06-20 07:44:33 +0000
  • 114d5b7c02 commit Ejiro Pinnock 2023-06-18 20:26:43 +0000
  • f2fcf02226 commit for model name and bound ip Ejiro Pinnock 2023-06-18 20:23:01 +0000
  • c0e5216987 commit for adding variables Ejiro Pinnock 2023-06-18 20:06:01 +0000
  • 502e5c9d7f commit for getting it running on h100 still slow Ejiro Pinnock 2023-06-18 19:57:51 +0000
  • ebea1a10e1 commit before running on gitpod Ejiro Pinnock 2023-06-18 17:11:22 +0000
  • b9d2c54114 temp fix cassanof 2023-06-18 04:08:33 -0700
  • a9d34708ad use right dtype cassanof 2023-06-18 04:07:12 -0700
  • 42bcfe7c23 change name cassanof 2023-06-18 03:59:21 -0700
  • 98bd65153a rem dangling import cassanof 2023-06-18 03:58:29 -0700
  • 020e32f7bf fix ciruclar cassanof 2023-06-18 03:57:39 -0700
  • e60072c524 move gen into class cassanof 2023-06-18 03:54:43 -0700
  • 97d5190a7c reqs for starchat? cassanof 2023-06-18 03:26:01 -0700
  • af90f4444d added model class cassanof 2023-06-18 03:23:57 -0700
  • dbfc7c6a4f runner cassanof 2023-06-18 03:08:17 -0700
  • 7953704f7a
         Merge 5ddc23d472 into f27481d8a3 Ali Mazloum 2023-06-16 10:53:01 -0400
  • 5ddc23d472
         Create SECURITY.md Ali Mazloum 2023-06-16 17:15:12 +0300
  • cdaec6c195 commit for local llm runs Ejiro Pinnock 2023-05-27 20:43:00 +0000
  • f27481d8a3
         Update README.md Shunyu Yao 2023-05-26 23:24:13 +0100
  • 9a9d7d8b2f demos Noah Shinn 2023-05-25 16:30:59 -0700
  • 0f7a737015 add runscripts Noah Shinn 2023-05-25 16:30:05 -0700
  • 6a8b75ccdd update citation Noah Shinn 2023-05-23 11:48:48 -0700
  • d876c4cdb4 Put HotPotQA on top Beck LaBash 2023-05-20 19:18:46 -0400
  • c2159d4b93 NBs and README Beck LaBash 2023-05-20 15:17:57 -0400
  • e531a5c0d6 Organize notebooks Beck LaBash 2023-05-19 22:36:05 -0400
  • 4924ce40f2 add logs Noah Shinn 2023-05-21 10:46:26 -0700
  • 245fd11901 move benchmarks to their place elleven11 2023-05-21 16:08:32 +0200
  • b6a324f78a start run instructions main-private Noah Shinn 2023-05-19 18:57:05 -0700
  • 34ab94a3b3 start run instructions Noah Shinn 2023-05-19 18:56:07 -0700
  • 5942b44c41 HotPotQA runs Beck LaBash 2023-05-19 21:32:30 -0400
  • 5269ef4ae0 start v2 Noah Shinn 2023-05-18 13:32:23 -0700
  • 970c487d97 reinit submodules elleven11 2023-05-21 15:51:39 +0200
  • a98e92b20a reset submodule elleven11 2023-05-21 15:49:43 +0200
  • 4e42b24dab start v2 Noah Shinn 2023-05-18 13:20:29 -0700
  • 878a144a66 alfworld and webshop Noah Shinn 2023-05-18 12:18:14 -0700
  • 3148695707 note about paper Noah Shinn 2023-04-09 02:18:52 -0400
  • a0162a065d update leetcode hard gym link Noah Shinn 2023-03-30 02:52:42 -0400
  • d2cdf66bc2 leetcode-hard gym repo Noah Shinn 2023-03-30 02:47:09 -0400
  • 9a71c64882 leetcode-hard gym repo Noah Shinn 2023-03-30 02:45:50 -0400
  • 62be0220db Put HotPotQA on top hotpot-notebooks Beck LaBash 2023-05-20 19:18:46 -0400
  • cf799785a6 NBs and README Beck LaBash 2023-05-20 15:17:57 -0400