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
492d4264
Commit
492d4264
authored
May 22, 2024
by
JessicaOjo
Browse files
edit for open models
parent
753e8670
Changes
2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
4 additions
and
4 deletions
+4
-4
lm_eval/tasks/afrixnli/manual/direct/afrixnli_manual_direct_yaml
.../tasks/afrixnli/manual/direct/afrixnli_manual_direct_yaml
+2
-2
lm_eval/tasks/afrixnli/manual/translate/afrixnli_manual_translate_yaml
.../afrixnli/manual/translate/afrixnli_manual_translate_yaml
+2
-2
No files found.
lm_eval/tasks/afrixnli/manual/direct/afrixnli_manual_direct_yaml
View file @
492d4264
...
...
@@ -4,7 +4,7 @@ group:
- afrixnli-manual
dataset_path: masakhane/afrixnli
dataset_name: null
output_type: multiple_choice
_gpt
output_type: multiple_choice
validation_split: validation
test_split: test
fewshot_split: validation
...
...
@@ -24,7 +24,7 @@ metric_list:
ignore_case: true
ignore_punctuation: true
- metric: acc
aggregation:
acc_gpt
aggregation:
mean
higher_is_better: true
ignore_case: true
ignore_punctuation: true
...
...
lm_eval/tasks/afrixnli/manual/translate/afrixnli_manual_translate_yaml
View file @
492d4264
...
...
@@ -5,7 +5,7 @@ group:
- afrixnli-translate-test
dataset_path: masakhane/afrixnli-translate-test
dataset_name: null
output_type: multiple_choice
_gpt
output_type: multiple_choice
test_split: test
doc_to_text: !function utils.doc_to_text
doc_to_target: !function utils.doc_to_target
...
...
@@ -23,7 +23,7 @@ metric_list:
ignore_case: true
ignore_punctuation: true
- metric: acc
aggregation:
acc_gpt
aggregation:
mean
higher_is_better: true
ignore_case: true
ignore_punctuation: true
...
...
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