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
ccca64f7
Unverified
Commit
ccca64f7
authored
Nov 07, 2023
by
Lintang Sutawika
Committed by
GitHub
Nov 07, 2023
Browse files
Merge branch 'big-refactor' into cont-metrics
parents
0a39d055
b7a4ea06
Changes
304
Expand all
Hide whitespace changes
Inline
Side-by-side
Showing
4 changed files
with
14 additions
and
13 deletions
+14
-13
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_us_foreign_policy.yaml
...mlu/flan_n_shot/loglikelihood/mmlu_us_foreign_policy.yaml
+6
-0
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_virology.yaml
...l/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_virology.yaml
+4
-2
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_world_religions.yaml
.../mmlu/flan_n_shot/loglikelihood/mmlu_world_religions.yaml
+4
-2
lm_eval/tasks/pubmedqa/preprocess_pubmedqa.py
lm_eval/tasks/pubmedqa/preprocess_pubmedqa.py
+0
-9
No files found.
lm_eval/tasks/mmlu/flan_n_shot/mmlu
_log
_us_foreign_policy.yaml
→
lm_eval/tasks/mmlu/flan_n_shot/
loglikelihood/
mmlu_us_foreign_policy.yaml
View file @
ccca64f7
This diff is collapsed.
Click to expand it.
lm_eval/tasks/mmlu/flan_n_shot/mmlu
_log
_virology.yaml
→
lm_eval/tasks/mmlu/flan_n_shot/
loglikelihood/
mmlu_virology.yaml
View file @
ccca64f7
This diff is collapsed.
Click to expand it.
lm_eval/tasks/mmlu/flan_n_shot/mmlu
_log
_world_religions.yaml
→
lm_eval/tasks/mmlu/flan_n_shot/
loglikelihood/
mmlu_world_religions.yaml
View file @
ccca64f7
This diff is collapsed.
Click to expand it.
lm_eval/tasks/pubmedqa/preprocess_pubmedqa.py
View file @
ccca64f7
This diff is collapsed.
Click to expand it.
Prev
1
…
12
13
14
15
16
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