Spaces:
Build error
Build error
Commit History
-
updated with meg's suggestions + cleaned up a bit
Clémentine412f8e5
-
eval_harness_v043_updates (#10)
Verified signature- Updates for newest lm_eval version, 0.4.3 (67a80c3deaeedce017896a57cc8c49a3d1a05bd2) - Minor import reordering (62c033216a47fba3781e9e05df0f05d1a3e66c3d) Co-authored-by: Margaret Mitchell <meg@users.noreply.huggingface.co>5375d59
-
Update src/envs.py
Verified signature5506f29
-
Renaming environ variable (#6)
Verified signature- Renaming environ variable (644021fad8a34f9f9cf8971c5e2a7c967aa0345e) Co-authored-by: Margaret Mitchell <meg@users.noreply.huggingface.co>fbede76 -
Update src/envs.py
Verified signaturedf9a594 -
adds variables EvalRequest is searching for (#8)
Verified signature- adds variables EvalRequest is searching for (249104f25d6652e429e5667985f14da0fe0c5307) Co-authored-by: Margaret Mitchell <meg@users.noreply.huggingface.co>e47a979
-
added doc
Clémentine7689092 -
simplified backend
Clémentine3e6770c
-
pr_3_add_button_readme_and_better_logs (#3)
Verified signature- Adding better readme (6a9c17dcb2c0970fff46a5f1fba87c2d4e1bd848) - Adding execute button (80a20422e63f5db2430aa8780d08df11bd7402bf) - Adding better logs (b2a9c221b75f4c63c7e74c5c56eb81aba74b93d2) - Adding better exception handling (8bd884a7f207ef9cec1c613edc89a9ff1725c843) - Adding reverse order (d38510d004f1574318e214adbc143776a71309d0) - Restructuring and adding download button (f59a2e9cf0439a833071d6f47dfdce948d2087de) - Ignore logfile (b149c0db43c5eba0158f0c392efea52e40b2d8c3) Co-authored-by: Derek Thomas <derek-thomas@users.noreply.huggingface.co>95c19d6 -
debug inference endpoint launch and requirements
Clémentine6bc96ff
-
adding_log_visualizer (#1)
Verified signature- Adding logging visualizer (a130fc382412b1c3f664e294da1aeb43ed30fa00) - Keeping default of checking every 10 min (ccb39b1f08fe0f04412d9e0401a1dc556b149fb0) - Increasing log lines to visualize (ef89b19123267a7694493f28cd25a8ac8ed4942b) - Adding better console handling (d800d714b0f2ae12ffaa23c053413f1951123238) Co-authored-by: Derek Thomas <derek-thomas@users.noreply.huggingface.co>8b88d2c -
Args is being accessed incorrectly (#2)
Verified signature- Args is being accessed incorrectly (2733d9bf4d777c3cc96f73e422ab9b61a7749143) Co-authored-by: Derek Thomas <derek-thomas@users.noreply.huggingface.co>1b74edb
-
force cleanup on failure
Clémentine1d6da9d -
changed default instance to cpu just in case
Clémentine6902167 -
added example for parameters
Clémentine18abd06 -
add logging back
Clémentine272ebb9 -
updated backend
Clémentine08ae6c5
-
CPU, TOKEN, env variables (#4)
Verified signature- Suggesting change for accidentally hard-coded environment variable (1190865ec3a7b3e156035aa2c793ba4ecd862235) - Adds CPU/Float32 support; adds user access Token passing; fixes hard-coded environment variable. (24b20ff4285a655000d36f4525e97131930257e8) - Just trying to open a PR without access to the org through the command line. (75324f0a44165244cedff94702842545307482b8) - Creating branch of changes through command line. (b8617767cc29e44c44d696c108152d8c0e9da21f) - Test (4e21c860af2562fa5ba7980b8b8a5684a5832387) - Remove tmp file (7599d4bb85377600cc1b63549a92669e53e9a20f) - Undo 1 change; keeping 'eval-queue' hard-coded. (cd4f3f159e844de76f32a79d75406a5ab18bfa30) - Undo 1 change; keeping 'eval-queue' hard-coded. (c0ed1f14cdcf8b3c7e5fa32b64818dfc83bf9bfd) Co-authored-by: Margaret Mitchell <meg@users.noreply.huggingface.co>55cc480
-
Update src/submission/check_validity.py
6eb8bfd
-
made token a requirement
Clémentinef982b8e -
test
Clémentinef0298e1
-
fix
Clémentinec15e77e -
removed quantization to simplify
Clémentineb899767 -
now with a functionning backend
Clémentine1ffc326
-
update read
Clémentine943f952 -
fixs
Clémentine314f91a -
updated leaderboard
Clémentineefeee6d -
Simplified leaderboard v0
Clémentine9833cdb -
simplified some parts of the code + updated requirements
Clémentine9d22eee -
Added check on tokenizer to prevent submissions which won't run
Clémentine7302987 -
Update benchmark count and fix typo (`inetuning->finetuning`) (#395)
- Update benchmark count and fix typo (`inetuning->finetuning`) (cdeea55b7621c0b1fa7515a40bf2fb50df62d5d7) Co-authored-by: Alvaro Bartolome <alvarobartt@users.noreply.huggingface.co>7abc6a7
-
fix order of request file vs request file list, to avoid resubmitting issues
Clémentine976f398 -
cache
Clémentine4ff9eef -
update for caching
Clémentine395eff6 -
add model architecture as column
Clémentine3dfaf22 -
Simplify About
Clémentineeaace79
-
Refactor 2 - added plotting back
ClémentineOnly takes into account last submissions, but we have no way to go back at eval date apart from loading info from git commit of results files. Also updated speed with gradio concurrency limit paramb1a1395 -
fix value error in param size
Clémentineccefec9 -
Fix requirements for mistral models - to change once transformers gets updated.
ClémentineWe need hf_hub >= 0.18 for collections, transformers >= 4.34 for mistral, and both depend on uncompatible versions of tokenizers. Installing transformers from a fork for now002172c
-
fix col width
Clémentinefc1e99b -
refacto style + rate limit
Clémentinedf66f6e -
Fix TruthfulQA NaN scores to 0
Clémentinebb17be3
-
refacto part 1
Clémentine2a5f9fb
-
add new evals to the leaderboard
Nathan Habibe3aaf53
-
token for checking gated base models
Clémentinef3cda22
-
Fix BibTex author ordering (#342)
- Fix BibTex author ordering (2edeb5ab568075636e23b5ecfd11c297c4425330) Co-authored-by: Lewis Tunstall <lewtun@users.noreply.huggingface.co>216309b -
fix disapearing models
Nathan Habib280033c
-
Merge branch 'main' of https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
Nathan Habib0f4fbd6 -
fix model display when fething metadata
Nathan Habib624b3c8
-
reorg to simplify nav in code base
Clémentine6e56e0d