Spaces:
Duplicated from datalawyer/legal_pt_llm_leaderboard

eduagarcia
/

open_pt_llm_leaderboard

Running on CPU Upgrade

App Files Files Community

open_pt_llm_leaderboard

Commit History

Add env variable SHOW_INCOMPLETE_EVALS and order evaluation queue by priority

8aaf0e7

eduagarcia commited on Feb 21

einops as requirement

0cc3edb

eduagarcia commited on Feb 21

Allow old model metrics

6269bd0

eduagarcia commited on Feb 17

changes pt_config

1a3f05a

eduagarcia commited on Feb 16

Add NPM field

f976f1c

eduagarcia commited on Feb 16

Add new tasks and make leadboard work without new tasks evals

5639a81

eduagarcia commited on Feb 16

add datasources links on the about page

03f7287

eduagarcia commited on Feb 16

add tags to README metadata

5fe4ee6

eduagarcia commited on Feb 15

fix bool env variabled

b81a33b

eduagarcia commited on Feb 15

fix eval time plot

0cb9327

eduagarcia commited on Feb 15

add changelog tab

b74e881

eduagarcia commited on Feb 15

Better about's

67cd6fc

eduagarcia commited on Feb 15

support hf leaderboard format and my format

a69553b

eduagarcia commited on Feb 6

minor fixes

79aba72

eduagarcia commited on Feb 6

Rename to Open PT LLM Leaderboard

1764c92

eduagarcia commited on Feb 5

diferentiate leaderboard upload from script upload

caef9bd

eduagarcia commited on Feb 5

Portuguese Tasks configs and fix bugs

c0fa950

eduagarcia commited on Feb 5

rorder initial_queue

0266144

eduagarcia commited on Jan 28

more models to initial_queue.jsonl

7084d46

eduagarcia commited on Jan 27

script for uploading initial request queue

559bd6b

eduagarcia commited on Jan 25

Fix typo on ModelType

155aef4

eduagarcia commited on Jan 25

New model_type: language adapt

395f537

eduagarcia commited on Jan 25

Add hidden option

b234783

eduagarcia commited on Jan 24

Refactor Tasks to load by yaml configuration file

4445ad2

eduagarcia commited on Jan 24

Feature: FIELD with original HF Leaderboard ranking

71ecfbb

eduagarcia commited on Jan 24

Remove default hide private or deleted

88c4c5f

eduagarcia commited on Jan 23

Merge Origin - Rename model types (#1)

9839977
verified

eduagarcia commited on Jan 23

Evaluation time metric and plot

359d8a9

eduagarcia commited on Jan 22

Add FAILED evaluations dropdown

ebb5810

eduagarcia commited on Jan 22

Add tiktoken for stabilityai/stablelm-2-1_6b and Qwen/Qwen-* models

ff9ccb0

eduagarcia commited on Jan 21

TRUST_REMOTE_CODE env variable

1253c3b

eduagarcia commited on Jan 21

default show private models

8df1d5c

eduagarcia commited on Jan 21

show baseline

1b2e131

eduagarcia commited on Jan 21

change icon to rocket

eef299c

eduagarcia commited on Jan 21

Fix model eval links and remove huggingface icon from Leaderboard name

439afd4

eduagarcia commited on Jan 21

Rename Leaderboard

7a2430c

eduagarcia commited on Jan 21

Parametrize documentation

7499b46

eduagarcia commited on Jan 21

New tasks difinitions

3449f84

eduagarcia commited on Jan 21

Refactor code for adding generic tasks

36e3010

eduagarcia commited on Jan 20

Makes Model Cards optional

5408125

eduagarcia commited on Jan 20

Enable clean initialization without any evaluate model

ec3a730

eduagarcia commited on Jan 19

ignore local env ad hub files

92ec1df

eduagarcia commited on Jan 19

Init dynamic_info if empty

68fa530

eduagarcia commited on Jan 19

Env variable for DYNAMIC_INFO_REPO

19a1194

eduagarcia commited on Jan 19

Unlimited request to HAS_HIGHER_RATE_LIMIT

5a43136

eduagarcia commited on Jan 19

Transfer main configs to ENV variables

1841941

eduagarcia commited on Jan 19

add mixtral to valid moe tags

a6f1b1f

Clémentine commited on Jan 18

fix typo 2

7dd994f

Clémentine commited on Jan 18

fix typo

9fc61c1

Clémentine commited on Jan 18

updated space restarts/jobs launches

5fd25b4

Clémentine commited on Jan 18