llama-cookbook
Eval reproduce recipe using lm-evaluation-harness and our 3.1 evals datasets
#627
Merged

Eval reproduce recipe using lm-evaluation-harness and our 3.1 evals datasets #627

HamidShojanazeri merged 37 commits into main from eval_reproduce
wukaixingxp
wukaixingxp first commit, local not working
9f0acebe
wukaixingxp eval working
37be8e99
wukaixingxp adding more on README
1f666708
wukaixingxp adding some fix
ed201fc8
wukaixingxp add result table to README
ff10442d
wukaixingxp changed requirement.txt for eval
48ea26cb
wukaixingxp add more on README
333aff70
wukaixingxp wukaixingxp requested a review from HamidShojanazeri HamidShojanazeri 1 year ago
wukaixingxp wukaixingxp assigned wukaixingxp wukaixingxp 1 year ago
facebook-github-bot facebook-github-bot added cla signed
wukaixingxp fix typo
cf0e715b
wukaixingxp refactor folder
307510b8
wukaixingxp fix typo and broken links
320f800b
wukaixingxp fixed dead link to pass lint check
c3f0dbfe
wukaixingxp fix typo
fe2b9f03
HamidShojanazeri
HamidShojanazeri commented on 2024-08-12
HamidShojanazeri
HamidShojanazeri commented on 2024-08-13
HamidShojanazeri
HamidShojanazeri commented on 2024-08-13
wukaixingxp now uses lm_eval cli instead
091f71e8
wukaixingxp fix typo
3bee947e
wukaixingxp fix dead links and typo
d095cd4c
wukaixingxp minor typo fix
9dcbca56
wukaixingxp wukaixingxp requested a review from raghotham raghotham 1 year ago
wukaixingxp wukaixingxp requested a review from rohit-ptl rohit-ptl 1 year ago
wukaixingxp added the issue link back
da9ab4b9
wukaixingxp fixing readme
9b8d6aa6
NathanHB
NathanHB commented on 2024-08-16
NathanHB
NathanHB commented on 2024-08-16
NathanHB
NathanHB commented on 2024-08-16
NathanHB
NathanHB commented on 2024-08-16
wukaixingxp changed readme and added more comments
eef8b888
wukaixingxp formating
38e6de84
wukaixingxp added Acknowledgement
178d2d98
nkcheng255 nkcheng255 requested a review from nkcheng255 nkcheng255 1 year ago
wukaixingxp wukaixingxp requested a review from init27 init27 1 year ago
wukaixingxp restructure readme
a42c0148
wukaixingxp fix typo
b9cb3555
wukaixingxp Merge branch 'main' into eval_reproduce
c1390e8c
wukaixingxp update instruction
19dd9dcd
wukaixingxp fixed commit and add nltk download
d691843a
wukaixingxp use pip install for lm_eval
d74507ac
wukaixingxp minor fix to readme
387fe503
wukaixingxp add word to wordlist
e3abfe76
init27
init27 approved these changes on 2024-08-20
wukaixingxp wukaixingxp requested a review from HamidShojanazeri HamidShojanazeri 1 year ago
HamidShojanazeri
HamidShojanazeri commented on 2024-08-20
HamidShojanazeri
HamidShojanazeri commented on 2024-08-21
wukaixingxp Update tools/benchmarks/llm_eval_harness/meta_eval_reproduce/README.md
08c739f4
wukaixingxp Update tools/benchmarks/llm_eval_harness/meta_eval_reproduce/README.md
14500686
wukaixingxp Update tools/benchmarks/llm_eval_harness/meta_eval_reproduce/README.md
f4d50d51
wukaixingxp Update tools/benchmarks/llm_eval_harness/meta_eval_reproduce/README.md
c32517b8
wukaixingxp Update tools/benchmarks/llm_eval_harness/meta_eval_reproduce/README.md
ef1f4c80
wukaixingxp Update tools/benchmarks/llm_eval_harness/meta_eval_reproduce/README.md
ae10920a
wukaixingxp minor fix to readme
25bb0c4e
wukaixingxp minor fix
e354eee1
HamidShojanazeri
HamidShojanazeri HamidShojanazeri merged b5f64c0b into main 1 year ago
HamidShojanazeri HamidShojanazeri deleted the eval_reproduce branch 1 year ago

Login to write a write a comment.

Login via GitHub

Assignees
Labels
Milestone