Hugging Face's logo

Spaces:
ludwigstumpp
/
llm-leaderboard
Running

App Files Community
1
llm-leaderboard

Commit History

Remove codeT results for code-davinci-002 as not comparable to other HumanEval results, due to additional explicit testing of outputs
72edf21

Ludwig Stumpp commited on

Add link to hf space
b7e4ee9

Ludwig Stumpp commited on

Replace commercial column with open
1c52cdd

Ludwig Stumpp commited on

Drop rows without any benchmarks
46d56b3

Ludwig Stumpp commited on

Add WinoGrande zero-shot and results
f452fea

Ludwig Stumpp commited on

Add WinoGrande few shot results for gpt4 and 3.5
eedd6a6

Ludwig Stumpp commited on

Drop columns after filtering for which there are no entries
7e2df21

Ludwig Stumpp commited on

Shown values in categorical filter now sorted
9770a07

Ludwig Stumpp commited on

For now set PaLM2 commercial use to no until clear
f3fd684

Ludwig Stumpp commited on

Starting to add PaLM2 benchmark results
fe8088e

Ludwig Stumpp commited on

Add download button for table + update todos
ea40e33

Ludwig Stumpp commited on

Check for bool dtype at table filter
7adf431

Ludwig Stumpp commited on

Add filtering by values
8658420

Ludwig Stumpp commited on

Add column for publisher
9d7638e

Ludwig Stumpp commited on

Add further results from HELM
8f06941

Ludwig Stumpp commited on

Add / modify gpt models according to HELM benchmark
4373b29

Ludwig Stumpp commited on

Clarifying gpt model names
669c882

Ludwig Stumpp commited on

Text work
84a7c6d

Ludwig Stumpp commited on

Fix GPT -3 commercial use
4d54a13

Ludwig Stumpp commited on

Add special thanks
d9a0906

Ludwig Stumpp commited on

Add replit code
8c37256

Ludwig Stumpp commited on

Add HellaSwag few shot
9e47a75

Ludwig Stumpp commited on

Add llama results on hellaswag zero shot
6147ea1

Ludwig Stumpp commited on

Add HellaSwag Benchmark
e1aeb72

Ludwig Stumpp commited on

Align human eval format
5e1e4f6

Ludwig Stumpp commited on

Add BLOOM model
360209c

Ludwig Stumpp commited on

Add MMLU few shot
9c17477

Ludwig Stumpp commited on

Add galactica model
21aaac9

Ludwig Stumpp commited on

Rearrange and link to open-llms repo
a60d3ed

Ludwig Stumpp commited on

Align writing
a3504d1

Ludwig Stumpp commited on

Adding missing links to eval scores for MLU task
f7cfe3e

Ludwig Stumpp commited on

Add column for commercial use + logic in streamlit app + disclaimer
5323497

Ludwig Stumpp commited on

Adding MMLU dataset and removing source table
c0dd25e

Ludwig Stumpp commited on

Add aditional LAMBADA entries
53be3b4

Ludwig Stumpp commited on

Add missing model sizes
3a7dc42

Ludwig Stumpp commited on

Add codex model
f3f17e5

Ludwig Stumpp commited on

Add HumanEval and Starcoder
49b476f

Ludwig Stumpp commited on

Remove whitespace
9a87dbf

Ludwig Stumpp commited on

Fix line break
305acd7

Ludwig Stumpp commited on

Text work
617d84c

Ludwig Stumpp commited on

Remove links in table headers
f3a8621

Ludwig Stumpp commited on

Add links
1d376a9

Ludwig Stumpp commited on

Text work
2591e9a

Ludwig Stumpp commited on

Switch back to markdown as easier diffable
908b597

Ludwig Stumpp commited on

Fix benchmark name
1df71ac

Ludwig Stumpp commited on

Add info about zero shot to leaderboard
73a321a

Ludwig Stumpp commited on

Move data files and specify as constant
48cd666

Ludwig Stumpp commited on

Add TriviaQA
ec21a67

Ludwig Stumpp commited on

Alignment of csv column names
0d59bb0

Ludwig Stumpp commited on

Text work
04eb23d

Ludwig Stumpp commited on