-
Notifications
You must be signed in to change notification settings - Fork 60
Insights: huggingface/lighteval
Overview
Loading
Could not load contribution data
Please try again later
Loading
5 Pull requests merged by 1 person
-
Fixing PIQA implementation
#222 merged
Jul 25, 2024 -
Fixes #165 - adds a check with generation length is not set by the user
#233 merged
Jul 24, 2024 -
Removes default bert scorer init
#234 merged
Jul 24, 2024 -
Remove the latex writer since we don't use it
#231 merged
Jul 23, 2024 -
Update issue templates
#235 merged
Jul 23, 2024
2 Pull requests opened by 1 person
-
Starting simpler programmatic interface
#236 opened
Jul 23, 2024 -
Use inference endpoints as judge
#237 opened
Jul 25, 2024
3 Issues closed by 1 person
-
What is `qem` for gsm8k evaluation?
#238 closed
Jul 25, 2024 -
The helm|piqa task is generative but has generation_size=-1.
#198 closed
Jul 25, 2024 -
`LatexTableWriter` created but never used.
#151 closed
Jul 23, 2024
1 Issue opened by 1 person
-
[FT] Caching
#239 opened
Jul 26, 2024
5 Unresolved conversations
Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.
-
adds llm as judge using transformers
#223 commented on
Jul 25, 2024 • 9 new comments -
Fixing issues with multichoice_continuations_start_space - was not parsed properly
#232 commented on
Jul 25, 2024 • 7 new comments -
A small improvement in `metrics_sample.py::ROUGE`
#217 commented on
Jul 24, 2024 • 0 new comments -
Tiny improvements to `endpoint_model.py`, `base_model.py`,...
#219 commented on
Jul 24, 2024 • 0 new comments -
Expose samples via the CLI
#228 commented on
Jul 25, 2024 • 0 new comments