Commit Graph

  • 4fae00b68b fix(ci): correct tag for checkout (#150) Aaron Pham 2023-07-25 14:11:03 -04:00
  • e0a90c8d7e infra: bump to dev version of 0.2.11.dev0 [generated] [skip ci] Aaron Pham 2023-07-25 17:03:38 +00:00
  • c97d39380c infra: prepare for release 0.2.10 [generated] [skip ci] v0.2.10 Aaron Pham 2023-07-25 16:49:50 +00:00
  • e000e7d1c6 fix(ci): release correct version via git Aaron 2023-07-25 12:46:08 -04:00
  • 6dc0bf0b12 fix: remove breakpoint on CLI aarnphm-ec2-dev 2023-07-25 16:30:16 +00:00
  • b23b59e1c9 fix(embeddings): correctly set JSON data via CLI client aarnphm-ec2-dev 2023-07-25 16:26:01 +00:00
  • 56bf84a760 fix(ci): make sure to exclude generated _version.py aarnphm-ec2-dev 2023-07-25 09:52:12 +00:00
  • 1940086bec feat(client): embeddings (#146) Aaron Pham 2023-07-25 05:44:21 -04:00
  • dcd34bd381 fix(build): running bento insider container (#141) Aaron Pham 2023-07-25 04:24:28 -04:00
  • afb2d34673 docs: update fine tuning model support (#145) Aaron Pham 2023-07-25 04:21:52 -04:00
  • a80fb4635d docs: remove extraneous whitespace (#144) Aaron Pham 2023-07-25 04:19:55 -04:00
  • c391717226 feat(ci): automatic release semver + git archival installation (#143) Aaron Pham 2023-07-25 04:18:49 -04:00
  • 5635ce8d87 infra: bump to dev version of 0.2.10.dev0 [generated] [skip ci] Aaron Pham 2023-07-24 23:35:04 +00:00
  • fb656164e1 infra: prepare for release 0.2.9 [generated] [skip ci] v0.2.9 Aaron Pham 2023-07-24 23:24:09 +00:00
  • 084786c898 fix(cli): `openllm models` for showing available aarnphm-ec2-dev 2023-07-24 22:58:14 +00:00
  • 0fe9d83ff3 docs: Update README.md (#139) Chaoyu 2023-07-24 15:11:20 -07:00
  • 60c725a21f ci: release PyPI before building binary (#138) Aaron Pham 2023-07-24 16:39:51 -04:00
  • e72f0d55f4 infra: bump to dev version of 0.2.9.dev0 [generated] [skip ci] Aaron Pham 2023-07-24 19:58:13 +00:00
  • 23a8ae44ed infra: prepare for release 0.2.8 [generated] [skip ci] v0.2.8 Aaron Pham 2023-07-24 19:44:11 +00:00
  • 7eabcd4355 feat: vLLM integration for PagedAttention (#134) Aaron Pham 2023-07-24 15:42:17 -04:00
  • 9afbdc5198 chore(deps): update bitsandbytes requirement from <0.40 to <0.42 (#137) dependabot[bot] 2023-07-24 07:59:50 +00:00
  • 4cd0784ee2 chore: export generation items for lazy loading aarnphm-ec2-dev 2023-07-23 06:50:00 +00:00
  • e2cdd767ef chore(cli): simplify table for `openllm models` aarnphm-ec2-dev 2023-07-23 06:29:58 +00:00
  • 693631958a feat(service): provisional API (#133) Aaron Pham 2023-07-23 02:15:39 -04:00
  • d88b069160 infra: bump to dev version of 0.2.8.dev0 [generated] [skip ci] Aaron Pham 2023-07-23 01:21:32 +00:00
  • b74bea36a7 infra: prepare for release 0.2.7 [generated] [skip ci] v0.2.7 Aaron Pham 2023-07-23 01:10:45 +00:00
  • 99bb0e4446 fix(serialisation): using save_pretrained with import_model aarnphm-ec2-dev 2023-07-23 01:07:39 +00:00
  • d4f3cf8b75 fix(llm): ignore quantization config when --quantize int4 is passed aarnphm-ec2-dev 2023-07-22 22:45:46 +00:00
  • 6f4c58175d chore(llm): add envvar for making tag aarnphm-ec2-dev 2023-07-22 21:37:19 +00:00
  • 57a0fec247 infra: bump to dev version of 0.2.7.dev0 [generated] [skip ci] Aaron Pham 2023-07-22 21:31:19 +00:00
  • 71689e506d infra: prepare for release 0.2.6 [generated] [skip ci] v0.2.6 Aaron Pham 2023-07-22 21:19:04 +00:00
  • 19f20c7dad perf(serialisation): implement wrapper to reduce callstack (#132) Aaron Pham 2023-07-22 17:15:03 -04:00
  • ecf31e90b7 chore(configuration): remove unused call Aaron 2023-07-22 15:25:44 -04:00
  • 31bd2fe31b chore(ci): better release flow (#131) Aaron Pham 2023-07-21 21:53:57 -04:00
  • beb8c2bb08 fix(ft): set report_to none to avoid wandb setup aarnphm-ec2-dev 2023-07-21 18:33:38 +00:00
  • 8a42832360 chore(ci): simplify bump dev workflow [skip ci] Aaron 2023-07-21 14:20:30 -04:00
  • 5d2dd470d0 infra: bump to dev version of 0.2.6.dev0 [generated] [skip ci] Aaron 2023-07-21 14:16:48 -04:00
  • d49ff95f7f infra: prepare for release 0.2.5 [generated] [skip ci] v0.2.5 Aaron Pham 2023-07-21 17:59:21 +00:00
  • 81b0451685 feat(cli): query with per request instruction (#130) Aaron Pham 2023-07-21 13:57:21 -04:00
  • 39f7725870 fix(ci): skip running actions on generated commit aarnphm-ec2-dev 2023-07-21 15:48:22 +00:00
  • aa32bfcc4d infra: bump to dev version of 0.2.5.dev0 [generated] aarnphm-ec2-dev 2023-07-21 15:45:13 +00:00
  • 6b61217523 infra: prepare for release 0.2.4 [generated] v0.2.4 Aaron Pham 2023-07-21 08:21:36 +00:00
  • e4ac0ed8b7 fix(cuda): support loading in single GPU aarnphm-ec2-dev 2023-07-21 08:10:01 +00:00
  • 8eb143ff60 fix(ci): remove unecessary semver check for release notes [skip ci] aarnphm-ec2-dev 2023-07-21 05:50:35 +00:00
  • 033358a991 infra: bump to dev version of 0.2.4.dev0 [generated] aarnphm-ec2-dev 2023-07-21 06:28:33 +00:00
  • e5cada218a infra: prepare for release 0.2.3 [generated] v0.2.3 Aaron Pham 2023-07-21 03:39:34 +00:00
  • 9ccbd60584 revert: include configuration to labels Aaron 2023-07-20 23:37:25 -04:00
  • f91e750fcd fix(build): remove configuration from labels aarnphm-ec2-dev 2023-07-21 03:30:59 +00:00
  • 347ffaadbe chore(playground): generate default dir to not set Aaron 2023-07-20 21:23:52 -04:00
  • f5b1c8ec1b fix(ft): correct set epochs args for TrainingArguments aarnphm-ec2-dev 2023-07-21 01:20:56 +00:00
  • ee7fa63a50 ci: using tokens for publishing (#129) Aaron Pham 2023-07-20 21:14:14 -04:00
  • 11f88b24ca infra: bump to dev version of 0.2.3.dev0 [generated] Aaron 2023-07-20 21:03:02 -04:00
  • 16118dd28f infra: prepare for release 0.2.2 [generated] v0.2.2 Aaron Pham 2023-07-21 00:46:36 +00:00
  • f56f8ee782 feat: fine-tuning script for LlaMA 2 (#128) Aaron Pham 2023-07-20 20:44:51 -04:00
  • c101103d37 infra: bump to dev version of 0.2.2.dev0 [generated] Aaron 2023-07-20 18:51:00 -04:00
  • 804b30adc4 infra: prepare for release 0.2.1 [generated] v0.2.1 Aaron Pham 2023-07-20 22:38:27 +00:00
  • 5189d2e721 fix(script): correct patch version for __about__.py Aaron 2023-07-20 18:34:53 -04:00
  • ea07ff6ce9 fix(llama): loose requirements for running llama in container aarnphm-ec2-dev 2023-07-20 22:07:14 +00:00
  • c88950655c fix(ci): make sure to run publish and dev prep correctly aarnphm-ec2-dev 2023-07-20 22:05:05 +00:00
  • b31cd0460b fix: correct tag inference for model-id aarnphm-ec2-dev 2023-07-20 21:40:56 +00:00
  • 3e50f0a851 fix(cli): implement latest bentoml 1.0.25 features aarnphm-ec2-dev 2023-07-20 20:51:27 +00:00
  • 858c2007c3 feat: revision parsed via model_id (#126) Aaron Pham 2023-07-20 14:36:53 -04:00
  • a056365d48 fix(ci): always run create coverage aarnphm-ec2-dev 2023-07-20 13:01:32 +00:00
  • 1b3508619e feat(llama): add default prompt for LlaMA-2 (#122) Aaron Pham 2023-07-20 07:46:33 -04:00
  • ee3a00514a infra: bump to dev version of 0.2.1dev0 [generated] aarnphm-ec2-dev 2023-07-20 00:02:45 +00:00
  • 5f874da4e2 fix: broken logics for upload aarnphm-ec2-dev 2023-07-19 23:55:35 +00:00
  • f9ca164e73 infra: prepare for release 0.2.0 [generated] v0.2.0 Aaron Pham 2023-07-19 23:43:52 +00:00
  • 292bca68c7 fix(ci): releas script correctly parse version aarnphm-ec2-dev 2023-07-19 23:41:33 +00:00
  • 4beb040cfd chore(ci): remove macos packaging aarnphm-ec2-dev 2023-07-19 23:25:12 +00:00
  • e69042a8e9 fix(script): not gpg signing tag aarnphm-ec2-dev 2023-07-19 23:12:04 +00:00
  • 9d28e0a1e6 fix(ci): disable gpg push aarnphm-ec2-dev 2023-07-19 23:09:12 +00:00
  • b747e3b4b8 fix(ci): remove signing aarnphm-ec2-dev 2023-07-19 23:01:23 +00:00
  • d92b136780 chore(llama): remove decapoda vairants Aaron 2023-07-19 18:58:04 -04:00
  • b6679be301 fix: release script not to signed Aaron 2023-07-19 18:48:01 -04:00
  • 8b340559aa fix(tests): skip running models tests on CI aarnphm-ec2-dev 2023-07-19 22:40:40 +00:00
  • e319a2977f fix(ci): editable install aarnphm-ec2-dev 2023-07-19 22:29:29 +00:00
  • c1ddb9ed7c feat: GPTQ + vLLM and LlaMA (#113) Aaron Pham 2023-07-19 18:12:12 -04:00
  • dbca689c65 chore(stubs): delete invalid stubs [skip ci] aarnphm-ec2-dev 2023-07-18 16:25:54 +00:00
  • b297ec1109 ci: pre-commit autoupdate [pre-commit.ci] (#119) pre-commit-ci[bot] 2023-07-17 16:29:29 -04:00
  • 9833d2f46f fix(ci): correct setup tests and auto-bot (#118) dependabot[bot] 2023-07-17 14:37:46 -04:00
  • 674d0c7c10 chore(ci): ignore pdm [skip ci] Aaron 2023-07-16 14:26:41 -04:00
  • 5bb95652db chore(ci): skip large models aarnphm-ec2-dev 2023-07-16 05:52:42 +00:00
  • fc963c42ce fix: build isolation (#116) Aaron Pham 2023-07-16 01:52:21 -04:00
  • fd9ae56812 fix(baichuan): add "cpm-kernel" as additional requirements (#117) HeTaoPKU 2023-07-16 11:16:05 +08:00
  • 09b0787306 feat(models): Baichuan (#115) HeTaoPKU 2023-07-16 10:01:37 +08:00
  • d37d14e52b fix(tests): mark package on CI to xfail aarnphm-ec2-dev 2023-07-15 12:48:28 +00:00
  • b2dba6143f fix(resource): correctly parse CUDA_VISIBLE_DEVICES (#114) Aaron Pham 2023-07-15 07:19:35 -04:00
  • b291526248 revert: remove badges Aaron Pham 2023-07-11 14:44:36 -04:00
  • e2ae24b74c fix(tests): building not being isolated aarnphm-ec2-dev 2023-07-11 17:28:00 +00:00
  • 2950cffd5b fix(save): set bento store and model store aarnphm-ec2-dev 2023-07-11 01:30:39 +00:00
  • cea082e7bd fix(cli): correct prune based on metadata aarnphm-ec2-dev 2023-07-11 00:34:22 +00:00
  • c2bb29b4f3 fix: building mpt dependencies aarnphm-ec2-dev 2023-07-11 00:21:23 +00:00
  • 61bfd64bd5 chore: decouple logs aarnphm-ec2-dev 2023-07-11 00:08:47 +00:00
  • cb2f030b5e fix: add bento tag for default --format container aarnphm-ec2-dev 2023-07-10 23:45:41 +00:00
  • 7824332a01 chore: remove auto workers aarnphm-ec2-dev 2023-07-10 21:51:12 +00:00
  • c7f4dc7bb2 feat(test): snapshot testing (#107) Aaron Pham 2023-07-10 17:23:19 -04:00
  • d3e4b95e84 ci: use trusted pypi publisher aarnphm-ec2-dev 2023-07-07 07:18:13 +00:00
  • fb849a384e feat: GPTNeoX (#106) Aaron Pham 2023-07-07 03:05:40 -04:00
  • f9af643479 fix(llm): auto import models for first time running aarnphm-ec2-dev 2023-07-06 13:40:57 +00:00
  • ec4293091d ci: wait for auto-bot to run check Aaron 2023-07-05 10:51:46 -04:00