mirror/OpenLLM
1
0
Fork 0
mirror of https://github.com/bentoml/OpenLLM.git synced 2026-03-11 19:47:03 -04:00
Code Issues Packages Projects Releases Wiki Activity
366 Commits 6 Branches 194 Tags
c1556642ae90ce0193ca7e8049f0c84495b83721
Commit Graph

278 Commits

Author SHA1 Message Date
Aaron
c1556642ae infra: bump to dev version of 0.1.15.dev0 [generated] 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-06-25 14:00:14 -04:00
Aaron Pham
e733fd55dc infra: prepare for release 0.1.14 [generated] 
Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>
 2023-06-25 17:55:43 +00:00
Aaron Pham
74fdd5e259 feat: release binary distribution (#66) 2023-06-25 10:38:03 -04:00
Aaron Pham
acb6a3cb32 fix: converting envvar to string (#68) 2023-06-25 03:40:45 -04:00
Aaron Pham
3593c764f0 fix(test): robustness (#64) 2023-06-24 11:10:07 -04:00
Aaron Pham
98328be394 peft(models): improve implementation (#60) 
If you have a local Dolly-V2 version, please do `openllm prune`
 2023-06-24 05:22:18 -04:00
Aaron Pham [bot]
3d9cc935d4 infra: bump to dev version of 0.1.14.dev0 [generated] 
Signed-off-by: Aaron Pham [bot] <29749331+aarnphm@users.noreply.github.com>
 2023-06-24 07:33:03 +00:00
Aaron Pham [bot]
91624580f3 infra: prepare for release 0.1.13 [generated] 
Signed-off-by: Aaron Pham [bot] <29749331+aarnphm@users.noreply.github.com>
 2023-06-24 07:29:20 +00:00
aarnphm-ec2-dev
3eac8cb12d fix(build): set null for first pass of service import 
Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
 2023-06-24 07:27:00 +00:00
Aaron Pham [bot]
0639c61941 infra: bump to dev version of 0.1.13.dev0 [generated] 
Signed-off-by: Aaron Pham [bot] <29749331+aarnphm@users.noreply.github.com>
 2023-06-24 01:30:31 +00:00
Aaron Pham [bot]
6268d00837 infra: prepare for release 0.1.12 [generated] 
Signed-off-by: Aaron Pham [bot] <29749331+aarnphm@users.noreply.github.com>
 2023-06-24 01:27:07 +00:00
Aaron Pham
1435478f6c fix(cli): ensure we parse tag for download (#58) 2023-06-23 21:24:53 -04:00
Aaron Pham
b2f7c77805 chore(cli): better command recommendation (#56) 2023-06-23 12:38:56 -04:00
Aaron Pham
dfca956fad feat: serve adapter layers (#52) 2023-06-23 10:07:15 -04:00
Zhao Shenyang
5981e49342 fix: correct bettertransformer envvar (#54) 2023-06-23 07:49:42 -04:00
Aaron Pham [bot]
464bfca81c infra: bump to dev version of 0.1.12.dev0 [generated] 
Signed-off-by: Aaron Pham [bot] <29749331+aarnphm@users.noreply.github.com>
 2023-06-23 05:21:19 +00:00
Aaron Pham [bot]
829f867645 infra: prepare for release 0.1.11 [generated] 
Signed-off-by: Aaron Pham [bot] <29749331+aarnphm@users.noreply.github.com>
 2023-06-23 05:18:00 +00:00
Aaron Pham
a30eebd56f feat(config): new class generation (#51) 
allow set up new class derived from base class with `model_derivate`.
 2023-06-23 01:15:38 -04:00
Aaron Pham
295fb5e7ea chore(cli): normalize kebab case (#50) 2023-06-22 23:50:32 -04:00
Aaron Pham [bot]
54be563b3e infra: bump to dev version of 0.1.11.dev0 [generated] 
Signed-off-by: Aaron Pham [bot] <29749331+aarnphm@users.noreply.github.com>
 2023-06-21 17:59:01 +00:00
Aaron Pham [bot]
5a69345d29 infra: prepare for release 0.1.10 [generated] 
Signed-off-by: Aaron Pham [bot] <29749331+aarnphm@users.noreply.github.com>
 2023-06-21 17:53:27 +00:00
Aaron
a85953d6bf fix(build): make sure not to overwrite missing openllm 
in build without dev mode

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-06-21 13:51:37 -04:00
Aaron Pham [bot]
703cb21e96 infra: bump to dev version of 0.1.10.dev0 [generated] 
Signed-off-by: Aaron Pham [bot] <29749331+aarnphm@users.noreply.github.com>
 2023-06-21 11:34:24 +00:00
Aaron Pham [bot]
278757d58a infra: prepare for release 0.1.9 [generated] 
Signed-off-by: Aaron Pham [bot] <29749331+aarnphm@users.noreply.github.com>
 2023-06-21 11:30:44 +00:00
aarnphm-ec2-dev
ef40fdf5c8 fix(build): quote environment variables 
Make sure that the config is quoted properly in generated Dockerfile

Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
 2023-06-21 11:28:37 +00:00
Aaron
de665def5c fix(cli): support loading model-id from local path 
SDK should already support loading from local-path, but on CLI there was
a bug with start where it sets the choice for model-id to only
pretrained set of model-id

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-06-21 07:26:12 -04:00
aarnphm-ec2-dev
d33149d758 fix(log): repr the given LLMConfig in debug mode 
Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
 2023-06-19 18:20:18 +00:00
Aaron Pham
ca802d9d1a fix: agent log (#37) 2023-06-19 14:11:39 -04:00
Aaron Pham [bot]
78a537079e infra: bump to dev version of 0.1.9.dev0 [generated] 
Signed-off-by: Aaron Pham [bot] <29749331+aarnphm@users.noreply.github.com>
 2023-06-19 18:08:32 +00:00
aarnphm-ec2-dev
70c7c0a9b7 fix(cli): use correct API for client 
Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
 2023-06-19 18:04:27 +00:00
Aaron Pham [bot]
6bbbefd06a infra: prepare for release 0.1.8 [generated] 
Signed-off-by: Aaron Pham [bot] <29749331+aarnphm@users.noreply.github.com>
 2023-06-19 18:02:08 +00:00
aarnphm-ec2-dev
6d43bdbcdb fix(instruct): remove breakpoint 
Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
 2023-06-19 18:00:00 +00:00
Aaron Pham [bot]
0e3f8d2fba infra: bump to dev version of 0.1.8.dev0 [generated] 
Signed-off-by: Aaron Pham [bot] <29749331+aarnphm@users.noreply.github.com>
 2023-06-19 17:30:50 +00:00
Aaron Pham [bot]
9a6af97356 infra: prepare for release 0.1.7 [generated] 
Signed-off-by: Aaron Pham [bot] <29749331+aarnphm@users.noreply.github.com>
 2023-06-19 17:27:52 +00:00
aarnphm-ec2-dev
feb0c53146 fix(timeout): increase default timeout to avoid asyncio error 
Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
 2023-06-19 17:02:42 +00:00
Aaron
58758f8241 fix(dolly_v2): gc collect after import 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-06-19 12:28:13 -04:00
Aaron
1ed0ae7787 fix(log): make sure to configure OpenLLM logs correctly 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-06-19 06:19:06 -04:00
Aaron
2244cce5bd fix(config): __getitem__ to get the value instead of member of class 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-06-19 05:35:11 -04:00
Aaron Pham
03758a5487 fix(tools): adhere to style guidelines (#31) 2023-06-18 20:03:17 -04:00
Aaron Pham
4fcd7c8ac9 integration: HuggingFace Agent (#29) 
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2023-06-18 00:13:53 -04:00
Aaron Pham [bot]
9be65a813b infra: bump to dev version of 0.1.7.dev0 [generated] 
Signed-off-by: Aaron Pham [bot] <29749331+aarnphm@users.noreply.github.com>
 2023-06-17 13:12:46 +00:00
Aaron Pham [bot]
ed398c38f8 infra: prepare for release 0.1.6 [generated] 
Signed-off-by: Aaron Pham [bot] <29749331+aarnphm@users.noreply.github.com>
 2023-06-17 13:02:47 +00:00
Aaron Pham
6f724416c0 perf: build quantization and better transformer behaviour (#28) 
Fixes quantization_config and low_cpu_mem_usage to be available on PyTorch implementation only

See changelog for more details on #28
 2023-06-17 08:56:14 -04:00
Aaron
233d4697b5 chore: update __all__ to take into _extra_objects 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-06-16 18:13:35 -04:00
Aaron Pham
ded8a9f809 feat: quantization (#27) 2023-06-16 18:10:50 -04:00
Aaron Pham
19bc7e3116 feat: fine-tuning [part 1] (#23) 2023-06-16 00:19:01 -04:00
Aaron
b9ff4ab92a chore: flatten examples llm-config 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-06-15 18:39:33 -04:00
Aaron
e4b7714756 chore(js): update metadata 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-06-15 13:18:05 -04:00
Aaron Pham
5e1445218b refactor: toplevel CLI (#26) 
Move up CLI outside of the factory function to simplify workflow
 2023-06-15 02:32:46 -04:00
Aaron Pham [bot]
9a6a976ce1 infra: bump to dev version of 0.1.6.dev0 [generated] 
Signed-off-by: Aaron Pham [bot] <29749331+aarnphm@users.noreply.github.com>
 2023-06-15 06:16:12 +00:00