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
23bd3449
"...targets/git@developer.sourcefind.cn:gaoqiong/migraphx.git" did not exist on "26277ec5c751e09148a9868e94709b34f4ca6f2f"
Commit
23bd3449
authored
Jun 24, 2024
by
Yu Shi Jie
Browse files
updated mmlu-pro to take on 3 splits: test, val, dev
parent
772d6f6f
Changes
3
Hide whitespace changes
Inline
Side-by-side
Showing
3 changed files
with
3 additions
and
3 deletions
+3
-3
lm_eval/tasks/mmlu_pro/default/_default_template_yaml
lm_eval/tasks/mmlu_pro/default/_default_template_yaml
+1
-1
lm_eval/tasks/mmlu_pro/flan_cot_fewshot/_mmlu_pro_flan_cot_fewshot_template_yaml
...flan_cot_fewshot/_mmlu_pro_flan_cot_fewshot_template_yaml
+1
-1
lm_eval/tasks/mmlu_pro/generative/_default_template_yaml
lm_eval/tasks/mmlu_pro/generative/_default_template_yaml
+1
-1
No files found.
lm_eval/tasks/mmlu_pro/default/_default_template_yaml
View file @
23bd3449
dataset_path: sjyuxyz/MMLU-Pro-with-subset
test_split: test
fewshot_split:
validation
fewshot_split:
dev
fewshot_config:
sampler: first_n
output_type: multiple_choice
...
...
lm_eval/tasks/mmlu_pro/flan_cot_fewshot/_mmlu_pro_flan_cot_fewshot_template_yaml
View file @
23bd3449
dataset_path: sjyuxyz/MMLU-Pro-with-subset
validation_split: validation
test_split: test
fewshot_split:
validation
fewshot_split:
dev
fewshot_config:
sampler: first_n
output_type: generate_until
...
...
lm_eval/tasks/mmlu_pro/generative/_default_template_yaml
View file @
23bd3449
dataset_path: sjyuxyz/MMLU-Pro-with-subset
test_split: test
fewshot_split:
validation
fewshot_split:
dev
fewshot_config:
sampler: first_n
output_type: generate_until
...
...
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