Spaces:

HuggingFaceH4
/

open_llm_leaderboard

Running

App Files Files Community

Resources

Show closed (8)

Add eval scores to model similar to spaces section

#38 opened about 9 hours ago by

SebastianSchramm

Falcon 7b Model Run Video & code

#37 opened about 17 hours ago by

decodingdatascience

Include number of likes in the leaderboard

#36 opened about 17 hours ago by

What about inference speed ?

#35 opened 1 day ago by

Model not found

#34 opened 2 days ago by

please include sambanovasystems/BLOOMChat-176B-v1

#33 opened 3 days ago by

Scores of GPT3.5 and GPT4 for comparison

#30 opened 4 days ago by

Possibly include multi-lingual benchmarks like C-Eval and XCopa

#29 opened 5 days ago by

The system message and prompt format for TruthfulQA results for Vicuna 13B

#28 opened 6 days ago by

Leaderboard is of very limited use without more 0-shot, instruction prompted datasets

#27 opened 7 days ago by

Why MMLU is so much lower than the results reported in some papers like LLama 65B

#26 opened 8 days ago by

Interesting stats

#25 opened 9 days ago by

Possibility to include benchmarks in other languages

#24 opened 9 days ago by

Request for access to raw dataset

#23 opened 10 days ago by

What if a model trained on one of the evaluation datasets?

#22 opened 10 days ago by

[Feature request] Search bar / regex for model

#21 opened 11 days ago by

how do you set task name for MMLU(5-shot) in LMEH?

#20 opened 16 days ago by

Stuck on 4bit?

#17 opened 17 days ago by

Progress is too slow

#16 opened 17 days ago by

Multilingual Scoreboard?

#15 opened 18 days ago by

[Bug] Average is taking empty columns as 0

#14 opened 20 days ago by

Column Request(s): VRAM usage, avg speed per inference,

#13 opened 20 days ago by

Add license/commercial use column?

#12 opened 21 days ago by

Adding more models

#11 opened 21 days ago by

Display when the evaluation was run

#10 opened 21 days ago by

[Feature] Add code evals section

#9 opened 21 days ago by

Inclusion of non open LLMs for straightforward comparison

#7 opened 21 days ago by

Show leaderboard position column

#6 opened 21 days ago by

Evaluation for fictional writing models

#5 opened 21 days ago by

Convert branch revision into commit revision

#4 opened 21 days ago by