Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
gaoqiong
lm-evaluation-harness
Commits
6653cc50
Commit
6653cc50
authored
Dec 30, 2021
by
Igor Ostrovsky
Browse files
Bump the version number for all tasks based on PerplexityTask
This is due to the change in the bits_per_byte calculation.
parent
38360512
Changes
2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
3 additions
and
3 deletions
+3
-3
lm_eval/tasks/pile.py
lm_eval/tasks/pile.py
+1
-1
lm_eval/tasks/wikitext.py
lm_eval/tasks/wikitext.py
+2
-2
No files found.
lm_eval/tasks/pile.py
View file @
6653cc50
...
...
@@ -10,7 +10,7 @@ from best_download import download_file
class
PilePerplexityTask
(
PerplexityTask
,
abc
.
ABC
):
VERSION
=
0
VERSION
=
1
PILE_SET_NAME
=
None
VAL_PATH
=
'data/pile/val.jsonl.zst'
...
...
lm_eval/tasks/wikitext.py
View file @
6653cc50
...
...
@@ -41,7 +41,7 @@ def wikitext_detokenizer(string):
class
WikiText
(
PerplexityTask
):
VERSION
=
0
VERSION
=
1
def
download
(
self
):
if
not
os
.
path
.
exists
(
'data/wikitext/wikitext-2-raw/wiki.valid.raw'
):
...
...
@@ -87,4 +87,4 @@ class WikiText(PerplexityTask):
def
count_words
(
self
,
doc
):
# count number of words in *original doc before detokenization*
return
len
(
re
.
split
(
r
"\s+"
,
doc
))
\ No newline at end of file
return
len
(
re
.
split
(
r
"\s+"
,
doc
))
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment