Merge branch 'big-refactor' of...

Merge branch 'big-refactor' of https://github.com/EleutherAI/lm-evaluation-harness into openai_completions

Merge branch 'big-refactor' of...
Merge branch 'big-refactor' of https://github.com/EleutherAI/lm-evaluation-harness into openai_completions
5d3bf2e7 · lintangsutawika · f66730c4 · bf26d979 · 5d3bf2e7 · 5d3bf2e7
Commit 5d3bf2e7 authored Nov 28, 2023 by lintangsutawika
14 changed files
--- a/lm_eval/tasks/bbh/flan_zeroshot/tracking_shuffled_objects_five_objects.yaml
+++ b/lm_eval/tasks/bbh/flan_zeroshot/tracking_shuffled_objects_five_objects.yaml
--- a/lm_eval/tasks/bbh/flan_zeroshot/tracking_shuffled_objects_seven_objects.yaml
+++ b/lm_eval/tasks/bbh/flan_zeroshot/tracking_shuffled_objects_seven_objects.yaml
--- a/lm_eval/tasks/bbh/flan_zeroshot/tracking_shuffled_objects_three_objects.yaml
+++ b/lm_eval/tasks/bbh/flan_zeroshot/tracking_shuffled_objects_three_objects.yaml
--- a/lm_eval/tasks/bbh/flan_zeroshot/web_of_lies.yaml
+++ b/lm_eval/tasks/bbh/flan_zeroshot/web_of_lies.yaml
--- a/lm_eval/tasks/bbh/flan_zeroshot/word_sorting.yaml
+++ b/lm_eval/tasks/bbh/flan_zeroshot/word_sorting.yaml
--- a/lm_eval/tasks/siqa/README.md
+++ b/lm_eval/tasks/siqa/README.md
--- a/lm_eval/tasks/siqa/bigbench.yml
+++ b/lm_eval/tasks/siqa/bigbench.yml
--- a/lm_eval/utils.py
+++ b/lm_eval/utils.py
--- a/pyproject.toml
+++ b/pyproject.toml
--- a/tests/models/test_gguf.py
+++ b/tests/models/test_gguf.py
--- a/tests/models/test_vllm.py
+++ b/tests/models/test_vllm.py
--- a/tests/testdata/gguf_test_44e268d15decc4d2d0f99e57e1476269826cd3b54262f7a0981f75ddd45b25d0.pkl
+++ b/tests/testdata/gguf_test_44e268d15decc4d2d0f99e57e1476269826cd3b54262f7a0981f75ddd45b25d0.pkl
--- a/tests/testdata/gguf_test_52ea409606de8755e03cf7c79f824101a4ce64bb6e6d3df556b8a4e7a5d92418.pkl
+++ b/tests/testdata/gguf_test_52ea409606de8755e03cf7c79f824101a4ce64bb6e6d3df556b8a4e7a5d92418.pkl
--- a/tests/testdata/gguf_test_8fcf3f2f52afeb2acd7c8e02c2cc3ce31a691b665d295f6c4e4bbd71c7caa1a2.pkl
+++ b/tests/testdata/gguf_test_8fcf3f2f52afeb2acd7c8e02c2cc3ce31a691b665d295f6c4e4bbd71c7caa1a2.pkl