- 27 Apr, 2022 19 commits
-
-
Stella Biderman authored
Pytest update
-
Stella Biderman authored
-
Stella Biderman authored
-
Stella Biderman authored
-
Stella Biderman authored
Update with new PR
-
Jonathan Tow authored
Enable saving all the examples.
-
cjlovering authored
-
cjlovering authored
-
cjlovering authored
-
Stella Biderman authored
Pulling eval harness updates
-
Charles Lovering authored
Use eval-hackathon branch for installing prompt-source.
-
Pawan Sasanka Ammanamanchi authored
-
cjlovering authored
- saves the doc idx by order in dataset - saves the full ctx. we can turn this off it is too much memory - saves the idx of the fewshot examples - saves the source (test/val) of the fewshot examples - TODO: We now need to return the pred/target from process_results - TODO: Make it so override-ed process-resutls don't have to re-impl this.
-
Charles Lovering authored
Add `ROUGE` metric to `PromptSourceTask`
-
-
jon-tow authored
-
jon-tow authored
-
Jonathan Tow authored
Updated the requests so that its easier to understand.
-
Tian Yun authored
-
- 26 Apr, 2022 21 commits
-
-
cjlovering authored
-
cjlovering authored
Updated doc: If the answer choices is empty, then it is generation; else ranked choice. This will be the canonical approach when using PS.
-
-
Tian Yun authored
-
jon-tow authored
-
Jonathan Tow authored
Add optional max length to generation.
-
cjlovering authored
-
cjlovering authored
-
cjlovering authored
-
-
jon-tow authored
-
cjlovering authored
-
cjlovering authored
-
Tian Yun authored
-
Tian Yun authored
-
Tian Yun authored
-
cjlovering authored
-
cjlovering authored
-
cjlovering authored
-
cjlovering authored
-
jon-tow authored
-