 Max Ryabinin
|
19d0e37839
Add a temporary hack for larger models
|
1 year ago |
|
Max Ryabinin
|
23e3f9a332
WIP try loading OPT-sized layers using BLOOM code
|
1 year ago |
|
Alexander Borzunov
|
c519bffc59
Bump version to 1.1.3 (#278)
|
1 year ago |
|
Alexander Borzunov
|
aae1f4f368
Increase default request_timeout (#276)
|
1 year ago |
|
justheuristic
|
fb2583b682
Use inference mode in _MergedInferenceStep (#275)
|
1 year ago |
|
Alexander Borzunov
|
fd9400b392
Fix use_chunked_forward="auto" on non-x86_64 machines (#267)
|
1 year ago |
|
Alexander Borzunov
|
a2e7f27a5a
Improve "connect your GPU" message (#266)
|
1 year ago |
|
Alexander Borzunov
|
fee19e9b9b
Use get_logger(__name__) instead of get_logger(__file__) (#265)
|
1 year ago |
|
Alexander Borzunov
|
55e7dc07a0
Limit max delay between retries to 15 min (#264)
|
1 year ago |
|
Alexander Borzunov
|
38b071135b
Show visible maddrs for public swarm too (#263)
|
1 year ago |
|
Alexander Borzunov
|
42594e5173
Link FAQ in readme (#260)
|
1 year ago |
|
Alexander Borzunov
|
2a5070aa1a
Improve reachability logs (#253)
|
1 year ago |
|
Alexander Borzunov
|
4091db10bf
Lower payload size threshold for stream handlers (#251)
|
1 year ago |
|
Alexander Borzunov
|
9954cb84fe
Add `allowed_servers`, `max_retries` options to the client, improve logs (#235)
|
1 year ago |
|
Alexander Borzunov
|
3c523ab0d2
Fix TP crashing when hypo_ids are used (#249)
|
1 year ago |
|
justheuristic
|
b8a6788490
Fix examples/sst, add cls_model embeddings (#248)
|
1 year ago |
|
justheuristic
|
8766a14d28
Minor changes to examples/prompt-tuning notebooks (#247)
|
1 year ago |
|
Alexander Borzunov
|
5367523df8
Fix typo in prompt-tuning-sst2.ipynb (#245)
|
1 year ago |
|
Alexander Borzunov
|
b03efb1ef5
Bump version to 1.1.2 (#244)
|
1 year ago |
|
Alexander Borzunov
|
5d7395e1b5
Prompt-tuning notebooks: suggest to use a smaller model for faster prototyping (#234)
|
1 year ago |
|
Artem Chumachenko
|
d4c687daca
Fix dtype error in fine-tuning notebooks (#231)
|
1 year ago |
|
Muhtasham Oblokulov
|
0ebf6de117
Add citation to readme (#219)
|
1 year ago |
|
justheuristic
|
c4938bc23e
Merge inference pools into one to increase inference speed (#225)
|
1 year ago |
|
Shuchang Zhou
|
3189b395f0
Fix a typo in error message (#227)
|
1 year ago |
|
Alexander Borzunov
|
fa5ac6e3b4
Mention BLOOMZ in readme (#221)
|
1 year ago |
|
Alexander Borzunov
|
e651d73f11
Add one more link to the "Getting started" tutorial (#218)
|
1 year ago |
|
Alexander Borzunov
|
af3da5bb04
Choose --num_blocks automatically for all models (#217)
|
1 year ago |
|
Alexander Borzunov
|
cea83d3356
Bump version to 1.1.1 (#214)
|
1 year ago |
|
Alexander Borzunov
|
702bb5a2c2
CI: Update deprecated actions, don't measure network RPS (#215)
|
1 year ago |
|
Alexander Borzunov
|
825f5dbf2d
CI: Convert model only when convert_model.py or setup.cfg change (#213)
|
1 year ago |
