Eval reproduce recipe using lm-evaluation-harness and our 3.1 evals datasets #627
first commit, local not working
9f0acebe
eval working
37be8e99
adding more on README
1f666708
adding some fix
ed201fc8
add result table to README
ff10442d
changed requirement.txt for eval
48ea26cb
add more on README
333aff70
fix typo
cf0e715b
refactor folder
307510b8
fix typo and broken links
320f800b
fixed dead link to pass lint check
c3f0dbfe
fix typo
fe2b9f03
now uses lm_eval cli instead
091f71e8
fix typo
3bee947e
fix dead links and typo
d095cd4c
minor typo fix
9dcbca56
added the issue link back
da9ab4b9
fixing readme
9b8d6aa6
changed readme and added more comments
eef8b888
formating
38e6de84
added Acknowledgement
178d2d98
restructure readme
a42c0148
fix typo
b9cb3555
Merge branch 'main' into eval_reproduce
c1390e8c
update instruction
19dd9dcd
fixed commit and add nltk download
d691843a
use pip install for lm_eval
d74507ac
minor fix to readme
387fe503
add word to wordlist
e3abfe76
init27
approved these changes
on 2024-08-20
Update tools/benchmarks/llm_eval_harness/meta_eval_reproduce/README.md
08c739f4
Update tools/benchmarks/llm_eval_harness/meta_eval_reproduce/README.md
14500686
Update tools/benchmarks/llm_eval_harness/meta_eval_reproduce/README.md
f4d50d51
Update tools/benchmarks/llm_eval_harness/meta_eval_reproduce/README.md
c32517b8
Update tools/benchmarks/llm_eval_harness/meta_eval_reproduce/README.md
ef1f4c80
Update tools/benchmarks/llm_eval_harness/meta_eval_reproduce/README.md
ae10920a
minor fix to readme
25bb0c4e
minor fix
e354eee1
Login to write a write a comment.
Login via GitHub