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
9822b06e
Unverified
Commit
9822b06e
authored
Mar 01, 2024
by
Lintang Sutawika
Committed by
GitHub
Mar 01, 2024
Browse files
Merge branch 'main' into weight_by_size
parents
51f27158
b177c82c
Changes
656
Hide whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
240 additions
and
80 deletions
+240
-80
lm_eval/tasks/mgsm/native_cot/mgsm_cot_native_de.yaml
lm_eval/tasks/mgsm/native_cot/mgsm_cot_native_de.yaml
+0
-8
lm_eval/tasks/mgsm/native_cot/mgsm_cot_native_en.yaml
lm_eval/tasks/mgsm/native_cot/mgsm_cot_native_en.yaml
+0
-8
lm_eval/tasks/mgsm/native_cot/mgsm_cot_native_es.yaml
lm_eval/tasks/mgsm/native_cot/mgsm_cot_native_es.yaml
+0
-8
lm_eval/tasks/mgsm/native_cot/mgsm_cot_native_fr.yaml
lm_eval/tasks/mgsm/native_cot/mgsm_cot_native_fr.yaml
+0
-8
lm_eval/tasks/mgsm/native_cot/mgsm_cot_native_ja.yaml
lm_eval/tasks/mgsm/native_cot/mgsm_cot_native_ja.yaml
+0
-8
lm_eval/tasks/mgsm/native_cot/mgsm_cot_native_ru.yaml
lm_eval/tasks/mgsm/native_cot/mgsm_cot_native_ru.yaml
+0
-8
lm_eval/tasks/mgsm/native_cot/mgsm_cot_native_sw.yaml
lm_eval/tasks/mgsm/native_cot/mgsm_cot_native_sw.yaml
+0
-8
lm_eval/tasks/mgsm/native_cot/mgsm_cot_native_te.yaml
lm_eval/tasks/mgsm/native_cot/mgsm_cot_native_te.yaml
+0
-8
lm_eval/tasks/mgsm/native_cot/mgsm_cot_native_th.yaml
lm_eval/tasks/mgsm/native_cot/mgsm_cot_native_th.yaml
+0
-8
lm_eval/tasks/mgsm/native_cot/mgsm_cot_native_zh.yaml
lm_eval/tasks/mgsm/native_cot/mgsm_cot_native_zh.yaml
+0
-8
lm_eval/tasks/mgsm/native_cot/mgsm_native_cot_bn.yaml
lm_eval/tasks/mgsm/native_cot/mgsm_native_cot_bn.yaml
+24
-0
lm_eval/tasks/mgsm/native_cot/mgsm_native_cot_de.yaml
lm_eval/tasks/mgsm/native_cot/mgsm_native_cot_de.yaml
+24
-0
lm_eval/tasks/mgsm/native_cot/mgsm_native_cot_en.yaml
lm_eval/tasks/mgsm/native_cot/mgsm_native_cot_en.yaml
+24
-0
lm_eval/tasks/mgsm/native_cot/mgsm_native_cot_es.yaml
lm_eval/tasks/mgsm/native_cot/mgsm_native_cot_es.yaml
+24
-0
lm_eval/tasks/mgsm/native_cot/mgsm_native_cot_fr.yaml
lm_eval/tasks/mgsm/native_cot/mgsm_native_cot_fr.yaml
+24
-0
lm_eval/tasks/mgsm/native_cot/mgsm_native_cot_ja.yaml
lm_eval/tasks/mgsm/native_cot/mgsm_native_cot_ja.yaml
+24
-0
lm_eval/tasks/mgsm/native_cot/mgsm_native_cot_ru.yaml
lm_eval/tasks/mgsm/native_cot/mgsm_native_cot_ru.yaml
+24
-0
lm_eval/tasks/mgsm/native_cot/mgsm_native_cot_sw.yaml
lm_eval/tasks/mgsm/native_cot/mgsm_native_cot_sw.yaml
+24
-0
lm_eval/tasks/mgsm/native_cot/mgsm_native_cot_te.yaml
lm_eval/tasks/mgsm/native_cot/mgsm_native_cot_te.yaml
+24
-0
lm_eval/tasks/mgsm/native_cot/mgsm_native_cot_th.yaml
lm_eval/tasks/mgsm/native_cot/mgsm_native_cot_th.yaml
+24
-0
No files found.
lm_eval/tasks/mgsm/native_cot/mgsm_cot_native_de.yaml
deleted
100644 → 0
View file @
51f27158
# Generated by utils.py
dataset_name
:
de
doc_to_target
:
'
{%
if
answer
is
not
none
%}{{answer[28+1]}}{%
else
%}{{answer_number|string}}{%
endif
%}'
doc_to_text
:
'
{%
if
answer
is
not
none
%}{{question+"\nSchritt-für-Schritt-Antwort:"}}{%
else
%}{{"Frage:
"+question+"\nSchritt-für-Schritt-Antwort:"}}{%
endif
%}'
include
:
cot_yaml
task
:
mgsm_de_native_cot
lm_eval/tasks/mgsm/native_cot/mgsm_cot_native_en.yaml
deleted
100644 → 0
View file @
51f27158
# Generated by utils.py
dataset_name
:
en
doc_to_target
:
'
{%
if
answer
is
not
none
%}{{answer[20+1]}}{%
else
%}{{answer_number|string}}{%
endif
%}'
doc_to_text
:
'
{%
if
answer
is
not
none
%}{{question+"\nStep-by-Step
Answer:"}}{%
else
%}{{"Question:
"+question+"\nStep-by-Step
Answer:"}}{%
endif
%}'
include
:
cot_yaml
task
:
mgsm_en_native_cot
lm_eval/tasks/mgsm/native_cot/mgsm_cot_native_es.yaml
deleted
100644 → 0
View file @
51f27158
# Generated by utils.py
dataset_name
:
es
doc_to_target
:
'
{%
if
answer
is
not
none
%}{{answer[22+1]}}{%
else
%}{{answer_number|string}}{%
endif
%}'
doc_to_text
:
'
{%
if
answer
is
not
none
%}{{question+"\nRespuesta
paso
a
paso:"}}{%
else
%}{{"Pregunta:
"+question+"\nRespuesta
paso
a
paso:"}}{%
endif
%}'
include
:
cot_yaml
task
:
mgsm_es_native_cot
lm_eval/tasks/mgsm/native_cot/mgsm_cot_native_fr.yaml
deleted
100644 → 0
View file @
51f27158
# Generated by utils.py
dataset_name
:
fr
doc_to_target
:
'
{%
if
answer
is
not
none
%}{{answer[25+1]}}{%
else
%}{{answer_number|string}}{%
endif
%}'
doc_to_text
:
'
{%
if
answer
is
not
none
%}{{question+"\nRéponse
étape
par
étape
:"}}{%
else
%}{{"Question
:
"+question+"\nRéponse
étape
par
étape
:"}}{%
endif
%}'
include
:
cot_yaml
task
:
mgsm_fr_native_cot
lm_eval/tasks/mgsm/native_cot/mgsm_cot_native_ja.yaml
deleted
100644 → 0
View file @
51f27158
# Generated by utils.py
dataset_name
:
ja
doc_to_target
:
'
{%
if
answer
is
not
none
%}{{answer[10+1]}}{%
else
%}{{answer_number|string}}{%
endif
%}'
doc_to_text
:
'
{%
if
answer
is
not
none
%}{{question+"\nステップごとの答え:"}}{%
else
%}{{"問題:
"+question+"\nステップごとの答え:"}}{%
endif
%}'
include
:
cot_yaml
task
:
mgsm_ja_native_cot
lm_eval/tasks/mgsm/native_cot/mgsm_cot_native_ru.yaml
deleted
100644 → 0
View file @
51f27158
# Generated by utils.py
dataset_name
:
ru
doc_to_target
:
'
{%
if
answer
is
not
none
%}{{answer[17+1]}}{%
else
%}{{answer_number|string}}{%
endif
%}'
doc_to_text
:
'
{%
if
answer
is
not
none
%}{{question+"\nПошаговоерешение:"}}{%
else
%}{{"Задача:
"+question+"\nПошаговоерешение:"}}{%
endif
%}'
include
:
cot_yaml
task
:
mgsm_ru_native_cot
lm_eval/tasks/mgsm/native_cot/mgsm_cot_native_sw.yaml
deleted
100644 → 0
View file @
51f27158
# Generated by utils.py
dataset_name
:
sw
doc_to_target
:
'
{%
if
answer
is
not
none
%}{{answer[24+1]}}{%
else
%}{{answer_number|string}}{%
endif
%}'
doc_to_text
:
'
{%
if
answer
is
not
none
%}{{question+"\nJibu
la
Hatua
kwa
Hatua:"}}{%
else
%}{{"Swali:
"+question+"\nJibu
la
Hatua
kwa
Hatua:"}}{%
endif
%}'
include
:
cot_yaml
task
:
mgsm_sw_native_cot
lm_eval/tasks/mgsm/native_cot/mgsm_cot_native_te.yaml
deleted
100644 → 0
View file @
51f27158
# Generated by utils.py
dataset_name
:
te
doc_to_target
:
'
{%
if
answer
is
not
none
%}{{answer[18+1]}}{%
else
%}{{answer_number|string}}{%
endif
%}'
doc_to_text
:
'
{%
if
answer
is
not
none
%}{{question+"\nదశలవారీగా
సమాధానం:"}}{%
else
%}{{"ప్రశ్న:
"+question+"\nదశలవారీగా
సమాధానం:"}}{%
endif
%}'
include
:
cot_yaml
task
:
mgsm_te_native_cot
lm_eval/tasks/mgsm/native_cot/mgsm_cot_native_th.yaml
deleted
100644 → 0
View file @
51f27158
# Generated by utils.py
dataset_name
:
th
doc_to_target
:
'
{%
if
answer
is
not
none
%}{{answer[17+1]}}{%
else
%}{{answer_number|string}}{%
endif
%}'
doc_to_text
:
'
{%
if
answer
is
not
none
%}{{question+"\nคำตอบทีละขั้นตอน:"}}{%
else
%}{{"โจทย์:
"+question+"\nคำตอบทีละขั้นตอน:"}}{%
endif
%}'
include
:
cot_yaml
task
:
mgsm_th_native_cot
lm_eval/tasks/mgsm/native_cot/mgsm_cot_native_zh.yaml
deleted
100644 → 0
View file @
51f27158
# Generated by utils.py
dataset_name
:
zh
doc_to_target
:
'
{%
if
answer
is
not
none
%}{{answer[5+1]}}{%
else
%}{{answer_number|string}}{%
endif
%}'
doc_to_text
:
'
{%
if
answer
is
not
none
%}{{question+"\n逐步解答:"}}{%
else
%}{{"问题:
"+question+"\n逐步解答:"}}{%
endif
%}'
include
:
cot_yaml
task
:
mgsm_zh_native_cot
lm_eval/tasks/mgsm/native_cot/mgsm_native_cot_bn.yaml
0 → 100644
View file @
9822b06e
# Generated by utils.py
dataset_name
:
bn
doc_to_target
:
'
{%
if
answer
is
not
none
%}{{answer[17:]}}{%
else
%}{{answer_number|string}}{%
endif
%}'
doc_to_text
:
'
{%
if
answer
is
not
none
%}{{question+"\nধাপে
ধাপে
উত্তর:"}}{%
else
%}{{"প্রশ্ন:
"+question+"\nধাপে
ধাপে
উত্তর:"}}{%
endif
%}'
filter_list
:
-
filter
:
-
function
:
regex
regex_pattern
:
The answer is (\-?[0-9\.\,]+)
-
function
:
take_first
name
:
strict-match
-
filter
:
-
function
:
regex
group_select
:
-1
regex_pattern
:
(-?[$0-9.,]{2,})|(-?[0-9]+)
-
function
:
take_first
name
:
flexible-extract
generation_kwargs
:
do_sample
:
false
until
:
-
'
প্রশ্ন:'
-
</s>
-
<|im_end|>
include
:
cot_yaml
task
:
mgsm_native_cot_bn
lm_eval/tasks/mgsm/native_cot/mgsm_native_cot_de.yaml
0 → 100644
View file @
9822b06e
# Generated by utils.py
dataset_name
:
de
doc_to_target
:
'
{%
if
answer
is
not
none
%}{{answer[29:]}}{%
else
%}{{answer_number|string}}{%
endif
%}'
doc_to_text
:
'
{%
if
answer
is
not
none
%}{{question+"\nSchritt-für-Schritt-Antwort:"}}{%
else
%}{{"Frage:
"+question+"\nSchritt-für-Schritt-Antwort:"}}{%
endif
%}'
filter_list
:
-
filter
:
-
function
:
regex
regex_pattern
:
Die Antwort lautet (\-?[0-9\.\,]+)
-
function
:
take_first
name
:
strict-match
-
filter
:
-
function
:
regex
group_select
:
-1
regex_pattern
:
(-?[$0-9.,]{2,})|(-?[0-9]+)
-
function
:
take_first
name
:
flexible-extract
generation_kwargs
:
do_sample
:
false
until
:
-
'
Frage:'
-
</s>
-
<|im_end|>
include
:
cot_yaml
task
:
mgsm_native_cot_de
lm_eval/tasks/mgsm/native_cot/mgsm_native_cot_en.yaml
0 → 100644
View file @
9822b06e
# Generated by utils.py
dataset_name
:
en
doc_to_target
:
'
{%
if
answer
is
not
none
%}{{answer[21:]}}{%
else
%}{{answer_number|string}}{%
endif
%}'
doc_to_text
:
'
{%
if
answer
is
not
none
%}{{question+"\nStep-by-Step
Answer:"}}{%
else
%}{{"Question:
"+question+"\nStep-by-Step
Answer:"}}{%
endif
%}'
filter_list
:
-
filter
:
-
function
:
regex
regex_pattern
:
The answer is (\-?[0-9\.\,]+)
-
function
:
take_first
name
:
strict-match
-
filter
:
-
function
:
regex
group_select
:
-1
regex_pattern
:
(-?[$0-9.,]{2,})|(-?[0-9]+)
-
function
:
take_first
name
:
flexible-extract
generation_kwargs
:
do_sample
:
false
until
:
-
'
Question:'
-
</s>
-
<|im_end|>
include
:
cot_yaml
task
:
mgsm_native_cot_en
lm_eval/tasks/mgsm/native_cot/mgsm_native_cot_es.yaml
0 → 100644
View file @
9822b06e
# Generated by utils.py
dataset_name
:
es
doc_to_target
:
'
{%
if
answer
is
not
none
%}{{answer[23:]}}{%
else
%}{{answer_number|string}}{%
endif
%}'
doc_to_text
:
'
{%
if
answer
is
not
none
%}{{question+"\nRespuesta
paso
a
paso:"}}{%
else
%}{{"Pregunta:
"+question+"\nRespuesta
paso
a
paso:"}}{%
endif
%}'
filter_list
:
-
filter
:
-
function
:
regex
regex_pattern
:
La respuesta es (\-?[0-9\.\,]+)
-
function
:
take_first
name
:
strict-match
-
filter
:
-
function
:
regex
group_select
:
-1
regex_pattern
:
(-?[$0-9.,]{2,})|(-?[0-9]+)
-
function
:
take_first
name
:
flexible-extract
generation_kwargs
:
do_sample
:
false
until
:
-
'
Pregunta:'
-
</s>
-
<|im_end|>
include
:
cot_yaml
task
:
mgsm_native_cot_es
lm_eval/tasks/mgsm/native_cot/mgsm_native_cot_fr.yaml
0 → 100644
View file @
9822b06e
# Generated by utils.py
dataset_name
:
fr
doc_to_target
:
'
{%
if
answer
is
not
none
%}{{answer[26:]}}{%
else
%}{{answer_number|string}}{%
endif
%}'
doc_to_text
:
'
{%
if
answer
is
not
none
%}{{question+"\nRéponse
étape
par
étape
:"}}{%
else
%}{{"Question
:
"+question+"\nRéponse
étape
par
étape
:"}}{%
endif
%}'
filter_list
:
-
filter
:
-
function
:
regex
regex_pattern
:
La réponse est (\-?[0-9\.\,]+)
-
function
:
take_first
name
:
strict-match
-
filter
:
-
function
:
regex
group_select
:
-1
regex_pattern
:
(-?[$0-9.,]{2,})|(-?[0-9]+)
-
function
:
take_first
name
:
flexible-extract
generation_kwargs
:
do_sample
:
false
until
:
-
'
Question
:'
-
</s>
-
<|im_end|>
include
:
cot_yaml
task
:
mgsm_native_cot_fr
lm_eval/tasks/mgsm/native_cot/mgsm_native_cot_ja.yaml
0 → 100644
View file @
9822b06e
# Generated by utils.py
dataset_name
:
ja
doc_to_target
:
'
{%
if
answer
is
not
none
%}{{answer[11:]}}{%
else
%}{{answer_number|string}}{%
endif
%}'
doc_to_text
:
'
{%
if
answer
is
not
none
%}{{question+"\nステップごとの答え:"}}{%
else
%}{{"問題:
"+question+"\nステップごとの答え:"}}{%
endif
%}'
filter_list
:
-
filter
:
-
function
:
regex
regex_pattern
:
答えは(\-?[0-9\.\,]+)です。
-
function
:
take_first
name
:
strict-match
-
filter
:
-
function
:
regex
group_select
:
-1
regex_pattern
:
(-?[$0-9.,]{2,})|(-?[0-9]+)
-
function
:
take_first
name
:
flexible-extract
generation_kwargs
:
do_sample
:
false
until
:
-
'
問題:'
-
</s>
-
<|im_end|>
include
:
cot_yaml
task
:
mgsm_native_cot_ja
lm_eval/tasks/mgsm/native_cot/mgsm_native_cot_ru.yaml
0 → 100644
View file @
9822b06e
# Generated by utils.py
dataset_name
:
ru
doc_to_target
:
'
{%
if
answer
is
not
none
%}{{answer[18:]}}{%
else
%}{{answer_number|string}}{%
endif
%}'
doc_to_text
:
'
{%
if
answer
is
not
none
%}{{question+"\nПошаговоерешение:"}}{%
else
%}{{"Задача:
"+question+"\nПошаговоерешение:"}}{%
endif
%}'
filter_list
:
-
filter
:
-
function
:
regex
regex_pattern
:
Ответ — (\-?[0-9\.\,]+)
-
function
:
take_first
name
:
strict-match
-
filter
:
-
function
:
regex
group_select
:
-1
regex_pattern
:
(-?[$0-9.,]{2,})|(-?[0-9]+)
-
function
:
take_first
name
:
flexible-extract
generation_kwargs
:
do_sample
:
false
until
:
-
'
Задача:'
-
</s>
-
<|im_end|>
include
:
cot_yaml
task
:
mgsm_native_cot_ru
lm_eval/tasks/mgsm/native_cot/mgsm_native_cot_sw.yaml
0 → 100644
View file @
9822b06e
# Generated by utils.py
dataset_name
:
sw
doc_to_target
:
'
{%
if
answer
is
not
none
%}{{answer[25:]}}{%
else
%}{{answer_number|string}}{%
endif
%}'
doc_to_text
:
'
{%
if
answer
is
not
none
%}{{question+"\nJibu
la
Hatua
kwa
Hatua:"}}{%
else
%}{{"Swali:
"+question+"\nJibu
la
Hatua
kwa
Hatua:"}}{%
endif
%}'
filter_list
:
-
filter
:
-
function
:
regex
regex_pattern
:
Jibu ni (\-?[0-9\.\,]+)
-
function
:
take_first
name
:
strict-match
-
filter
:
-
function
:
regex
group_select
:
-1
regex_pattern
:
(-?[$0-9.,]{2,})|(-?[0-9]+)
-
function
:
take_first
name
:
flexible-extract
generation_kwargs
:
do_sample
:
false
until
:
-
'
Swali:'
-
</s>
-
<|im_end|>
include
:
cot_yaml
task
:
mgsm_native_cot_sw
lm_eval/tasks/mgsm/native_cot/mgsm_native_cot_te.yaml
0 → 100644
View file @
9822b06e
# Generated by utils.py
dataset_name
:
te
doc_to_target
:
'
{%
if
answer
is
not
none
%}{{answer[19:]}}{%
else
%}{{answer_number|string}}{%
endif
%}'
doc_to_text
:
'
{%
if
answer
is
not
none
%}{{question+"\nదశలవారీగా
సమాధానం:"}}{%
else
%}{{"ప్రశ్న:
"+question+"\nదశలవారీగా
సమాధానం:"}}{%
endif
%}'
filter_list
:
-
filter
:
-
function
:
regex
regex_pattern
:
సమాధానం (\-?[0-9\.\,]+)
-
function
:
take_first
name
:
strict-match
-
filter
:
-
function
:
regex
group_select
:
-1
regex_pattern
:
(-?[$0-9.,]{2,})|(-?[0-9]+)
-
function
:
take_first
name
:
flexible-extract
generation_kwargs
:
do_sample
:
false
until
:
-
'
ప్రశ్న:'
-
</s>
-
<|im_end|>
include
:
cot_yaml
task
:
mgsm_native_cot_te
lm_eval/tasks/mgsm/native_cot/mgsm_native_cot_th.yaml
0 → 100644
View file @
9822b06e
# Generated by utils.py
dataset_name
:
th
doc_to_target
:
'
{%
if
answer
is
not
none
%}{{answer[18:]}}{%
else
%}{{answer_number|string}}{%
endif
%}'
doc_to_text
:
'
{%
if
answer
is
not
none
%}{{question+"\nคำตอบทีละขั้นตอน:"}}{%
else
%}{{"โจทย์:
"+question+"\nคำตอบทีละขั้นตอน:"}}{%
endif
%}'
filter_list
:
-
filter
:
-
function
:
regex
regex_pattern
:
คำตอบคือ (\-?[0-9\.\,]+)
-
function
:
take_first
name
:
strict-match
-
filter
:
-
function
:
regex
group_select
:
-1
regex_pattern
:
(-?[$0-9.,]{2,})|(-?[0-9]+)
-
function
:
take_first
name
:
flexible-extract
generation_kwargs
:
do_sample
:
false
until
:
-
'
โจทย์:'
-
</s>
-
<|im_end|>
include
:
cot_yaml
task
:
mgsm_native_cot_th
Prev
1
…
20
21
22
23
24
25
26
27
28
…
33
Next
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