Commit Graph

  • 3b040e8e0f update patcher hiyouga 2024-06-19 21:27:00 +08:00
  • 42e69a3c63 set dev version hiyouga 2024-06-19 21:08:16 +08:00
  • 87e330fee5 Update publish.yml hiyouga 2024-06-19 20:46:33 +08:00
  • 71327ba85a release v0.8.2 hiyouga 2024-06-19 20:42:09 +08:00
  • 2b596fb55f fix jinja template hiyouga 2024-06-19 20:03:50 +08:00
  • 4cff6a4ad5 fix templates hiyouga 2024-06-19 17:44:05 +08:00
  • c48cbc371d update wechat_npu.jpg codingma 2024-06-19 14:02:24 +08:00
  • 5c2ff1b749 Cleaner integration. Jonery 2024-06-19 12:29:40 +08:00
  • 6d2bf216ac fix bug hiyouga 2024-06-19 03:49:23 +08:00
  • 4f22eae8f4 use prefix to replace force system hiyouga 2024-06-19 03:39:52 +08:00
  • cd75b1fe9d fix tool formatter, allow parallel function #4362 hiyouga 2024-06-19 03:23:51 +08:00
  • c0ca42566c Merge pull request #4173 from mMrBun/main hoshi-hiyouga 2024-06-19 03:18:55 +08:00
  • 9ab0401948 update data hiyouga 2024-06-19 02:48:43 +08:00
  • 344b9a36b2 tiny fix hiyouga 2024-06-18 23:32:18 +08:00
  • 89a50dbfde Merge pull request #4314 from EliMCosta/patch-2 hoshi-hiyouga 2024-06-18 23:30:59 +08:00
  • 10316dd8ca Merge pull request #4309 from EliMCosta/patch-1 hoshi-hiyouga 2024-06-18 23:30:19 +08:00
  • a233fbc258 add deepseek coder v2 #4346 hiyouga 2024-06-18 22:53:54 +08:00
  • 4bd77d8563 fix #4357 hiyouga 2024-06-18 22:42:45 +08:00
  • 078040babd Merge pull request #4334 from zzxzz12345/bugfix/add-pandas-versions hoshi-hiyouga 2024-06-18 22:30:35 +08:00
  • e8c518c08a Update requirements.txt hoshi-hiyouga 2024-06-18 22:27:24 +08:00
  • c96264bc47 fix #4335 hiyouga 2024-06-18 22:08:56 +08:00
  • 97c5235160 add example Jonery 2024-06-18 13:50:26 +08:00
  • 8f7c78b641 fix typo Jonery 2024-06-18 12:39:26 +08:00
  • 0f72aac8c9 Support distributed BAdam. Jonery 2024-06-18 12:27:47 +08:00
  • 24c160df3d lint hiyouga 2024-06-17 22:35:56 +08:00
  • 7857c0990b update chat engine #4335 hiyouga 2024-06-17 19:07:17 +08:00
  • fcb2e8e7b7 update readme hiyouga 2024-06-17 18:47:24 +08:00
  • ea1f3ba5e0 Merge remote-tracking branch 'upstream/main' Jonery 2024-06-17 18:44:51 +08:00
  • b2fc9cc15f update gitigore Jonery 2024-06-17 18:29:36 +08:00
  • 33b4372778 adapt for badam with ds zero3 Jonery 2024-06-17 18:18:10 +08:00
  • e2665e71c7 fix #4326 hiyouga 2024-06-17 18:17:48 +08:00
  • 72471ee046 Update wechat.jpg hiyouga 2024-06-17 17:49:03 +08:00
  • 2bf2863a58 tiny fix hiyouga 2024-06-17 17:47:25 +08:00
  • 12869c3ede Update requirements.txt 胡翀 2024-06-17 16:45:57 +08:00
  • df12621dae Fix Dockerfile Eli Costa 2024-06-16 19:16:23 -03:00
  • 3ec57ac239 Update README_zh.md Eli Costa 2024-06-16 11:34:31 -03:00
  • 82d5c5c1e8 Update README_zh.md Eli Costa 2024-06-16 11:22:06 -03:00
  • 103664203c Update README.md Eli Costa 2024-06-16 11:19:25 -03:00
  • 74e49cca95 Add Magpie and Webinstruct dataset samples Eli Costa 2024-06-15 19:31:56 -03:00
  • 238f5c3d99 update packing with sdpa and eager attention mode ancv 2024-06-16 02:25:47 +07:00
  • 29c1f31baa Update parser.py hoshi-hiyouga 2024-06-16 02:57:00 +08:00
  • 0a2ec5fe20 update pr template hiyouga 2024-06-16 01:43:43 +08:00
  • b7b5892a34 Merge pull request #4307 from hiyouga/pissa hoshi-hiyouga 2024-06-16 01:41:50 +08:00
  • 46093b5786 fix tol hiyouga 2024-06-16 01:38:44 +08:00
  • 7f3c19e3ab Update tests.yml hiyouga 2024-06-16 01:22:23 +08:00
  • de43bee0b0 increase tol hiyouga 2024-06-16 01:21:06 +08:00
  • 8c1046d78a support pissa hiyouga 2024-06-16 01:08:12 +08:00
  • 38b6b0f52e tiny fix hiyouga 2024-06-16 01:06:41 +08:00
  • 04315c3d92 remove some unused params ancv 2024-06-15 23:00:55 +07:00
  • 80a9e6bf94 use fixture hiyouga 2024-06-15 20:06:17 +08:00
  • 1b834f50be add tests hiyouga 2024-06-15 19:51:20 +08:00
  • 572d8bbfdd add minicpm #4227 hiyouga 2024-06-15 17:58:52 +08:00
  • d87108daa6 add license hiyouga 2024-06-15 17:54:33 +08:00
  • acd84ce535 update readme hiyouga 2024-06-15 05:13:16 +08:00
  • f1aa6a411a fix #4271 hiyouga 2024-06-15 05:11:33 +08:00
  • d519b4d76d disable DP hiyouga 2024-06-15 04:57:19 +08:00
  • 9092f963db fix #4292 hiyouga 2024-06-15 04:47:13 +08:00
  • 78589cf90c fix #4295 hiyouga 2024-06-15 04:34:55 +08:00
  • b27269bd2b add test cases hiyouga 2024-06-15 04:05:54 +08:00
  • 2d43b8bb49 Update README.md hiyouga 2024-06-13 16:02:21 +08:00
  • 892e561c28 update examples hiyouga 2024-06-13 03:26:10 +08:00
  • c94e6c9411 add quant check in webui export tab hiyouga 2024-06-13 03:19:18 +08:00
  • a19cdd39fe Update llama3_full_sft_ds3.yaml hiyouga 2024-06-13 03:16:20 +08:00
  • b6e008c152 update examples hiyouga 2024-06-13 03:15:06 +08:00
  • 6baafd4eb3 fix #4221 hiyouga 2024-06-13 02:48:21 +08:00
  • 9419f96609 update wechat hiyouga 2024-06-13 02:31:45 +08:00
  • cf9f2d6c42 fix #4209 hiyouga 2024-06-13 02:25:50 +08:00
  • 2ed8270112 clean code hiyouga 2024-06-13 01:58:16 +08:00
  • 1f23f25226 Merge pull request #4246 from hzhaoy/adapt-vllm-v0.5.0 hoshi-hiyouga 2024-06-13 01:54:02 +08:00
  • c7a5620ccc add neo-sft dataset hiyouga 2024-06-13 01:00:56 +08:00
  • 713fde4259 fix lint hiyouga 2024-06-13 00:48:44 +08:00
  • 947a34f53b fix docker compose usage hiyouga 2024-06-13 00:07:48 +08:00
  • 8fb6366ebe adapt vllm==0.5.0 hzhaoy 2024-06-12 18:29:03 +08:00
  • 2ce2e5bc47 update readme hiyouga 2024-06-12 17:39:12 +08:00
  • 577de2fa07 fix #4242 hiyouga 2024-06-12 16:50:11 +08:00
  • 656b2bbdaf Merge pull request #4234 from kimdwkimdw/patch-1 hoshi-hiyouga 2024-06-12 16:39:09 +08:00
  • d65a3f7cb6 Support vllm==0.5.0 Arthur Kim 2024-06-12 16:49:12 +09:00
  • b2c367bc61 implement efficient packing without cross-contamination attention ancv 2024-06-12 11:56:01 +07:00
  • 557891debb update wechat_npu.jpg codingma 2024-06-12 10:39:05 +08:00
  • 9049aab911 Merge pull request #4204 from dignfei/main hoshi-hiyouga 2024-06-11 17:06:10 +08:00
  • 0c29233237 Update pretrain.py hoshi-hiyouga 2024-06-11 17:02:14 +08:00
  • cca6f35108 fix deepspeed version hiyouga 2024-06-11 16:52:36 +08:00
  • 6979f3f848 经过大量的增量预训练,进行对比试验,发现这个bug:llama3在预训练时使用的tokenizer.eos_toke是'<|end_of_text|>' ,这里在每条数据后面也得用这个,而不是'<|eot_id|>',否则很容易导致严重的性能下降 d 2024-06-11 16:21:48 +08:00
  • 53b74361d3 Update bug-report.yml hiyouga 2024-06-11 15:40:21 +08:00
  • 89f2bd8c8c fix #4198 hiyouga 2024-06-11 15:38:38 +08:00
  • 90e14a960d tiny fix hiyouga 2024-06-11 12:48:53 +08:00
  • 796699f867 Merge pull request #4191 from iamthebot/al--add_manifest_for_reqs hoshi-hiyouga 2024-06-11 10:41:15 +08:00
  • 5f7b3b3ff6 add manifest so requirements.txt in sdist Alfredo Luque 2024-06-11 00:07:06 +00:00
  • 3f24337a8a tiny fix hiyouga 2024-06-11 01:04:16 +08:00
  • 91e62a098f set dev version hiyouga 2024-06-11 00:50:53 +08:00
  • 2b6ebd6b51 release v0.8.1 hiyouga 2024-06-11 00:44:26 +08:00
  • a793e8456b fix #4160 hiyouga 2024-06-11 00:37:17 +08:00
  • 949e9908ad fix #4145 hiyouga 2024-06-11 00:19:17 +08:00
  • 0012762b04 update evaluator hiyouga 2024-06-10 23:56:00 +08:00
  • c907d81667 fix #2666 hiyouga 2024-06-10 21:24:15 +08:00
  • ef4afdaf0e Merge pull request #4167 from yzoaim/branch hoshi-hiyouga 2024-06-10 16:24:33 +08:00
  • 950e360ca0 Optimize the handling of QWEN2 in scenarios involving multiple tool calls. mMrBun 2024-06-10 02:00:14 +08:00
  • 6ed0b0c800 Removed unnecessary comments. mMrBun 2024-06-09 18:25:22 +08:00
  • 0f2609ce19 Merge branch 'hiyouga:main' into main mMrBun 2024-06-09 18:17:24 +08:00
  • cb1cbcb293 Implemented the tool_formatter and tool_extractor for glm4 tool_format mMrBun 2024-06-09 18:16:15 +08:00