Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Reorganize assets and unify naming scheme #191

Merged
merged 26 commits into from
Sep 6, 2023
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
26 commits
Select commit Hold shift + click to select a range
1abba38
Reorganize assets and unify naming scheme
fdalvi Aug 31, 2023
f34563f
Remove duplicate GPT4 propaganda asset
fdalvi Aug 31, 2023
1bc0e72
Remove duplicate GPT3.5 harmfulness detection asset
fdalvi Aug 31, 2023
ccafb6f
Remove duplicate GPT3.5 claim detection asset, and unify naming schem…
fdalvi Aug 31, 2023
f51a7b2
Add missing Lemmatization assets for BLOOMZ and GPT4
fdalvi Aug 31, 2023
91114a0
Rename gender assets to remove redundant 'Gender' prefix
fdalvi Sep 3, 2023
ae2039a
Rename CT22/CT23/Propaganda datasets
fdalvi Sep 4, 2023
76627b9
Fix language codes and format code
fdalvi Sep 5, 2023
8dd5674
Fix HateSpeech and Offensive dataset names
fdalvi Sep 4, 2023
8a026cc
Fix Parsing citations and dataset name
fdalvi Sep 4, 2023
09eb723
Fix ArSAS dataset name
fdalvi Sep 4, 2023
eade9de
Fix ADI dataset name
fdalvi Sep 4, 2023
4dfd74a
Fix default label type in Propaganda task
fdalvi Sep 5, 2023
2bf2d03
Fix incorrect Dataset in Harmful GPT4 asset
fdalvi Sep 5, 2023
f78c7f9
renamed datasets, assets and tasks for stance and fact.
MaramHasanain Sep 5, 2023
db99243
Fix Lemmatization dataset name and citation
fdalvi Sep 5, 2023
d699309
Format code
fdalvi Sep 5, 2023
7c119a1
Fix Diacritization dataset name and citation
fdalvi Sep 5, 2023
5b4e44f
Add Dialectal Diacritization dataset and asset
fdalvi Sep 5, 2023
c0ccc42
Add GPT4 diacritization assets
fdalvi Sep 5, 2023
4bd2ec1
Split segmentation assets across correct datasets
fdalvi Sep 5, 2023
e474c39
Split POS assets across correct datasets and add proper citations
fdalvi Sep 5, 2023
e812c9d
Merged similar tasks and updated assets
MaramHasanain Sep 5, 2023
bd8ae2b
Format code
fdalvi Sep 6, 2023
f4349f3
Rename STS assets to match convention
fdalvi Sep 6, 2023
d14d5be
Merge branch 'main' into maintenance/reorganize_assets
fdalvi Sep 6, 2023
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
@@ -1,13 +1,13 @@
import os

from llmebench.datasets import AttentionworthyDataset
from llmebench.datasets import CT22AttentionworthyDataset
from llmebench.models import BLOOMPetalModel
from llmebench.tasks import AttentionworthyTask


def config():
return {
"dataset": AttentionworthyDataset,
"dataset": CT22AttentionworthyDataset,
"dataset_args": {},
"task": AttentionworthyTask,
"task_args": {},
Expand Down
Original file line number Diff line number Diff line change
@@ -1,14 +1,14 @@
import os
import re

from llmebench.datasets import AttentionworthyDataset
from llmebench.models import GPTModel, RandomGPTModel
from llmebench.datasets import CT22AttentionworthyDataset
from llmebench.models import GPTModel
from llmebench.tasks import AttentionworthyTask


def config():
return {
"dataset": AttentionworthyDataset,
"dataset": CT22AttentionworthyDataset,
"dataset_args": {},
"task": AttentionworthyTask,
"task_args": {},
Expand Down
Original file line number Diff line number Diff line change
@@ -1,18 +1,13 @@
import os
import random
import re

from llmebench.datasets import AttentionworthyDataset
from llmebench.datasets import CT22AttentionworthyDataset
from llmebench.models import GPTChatCompletionModel
from llmebench.tasks import AttentionworthyTask


random.seed(1333)


def config():
return {
"dataset": AttentionworthyDataset,
"dataset": CT22AttentionworthyDataset,
"dataset_args": {},
"task": AttentionworthyTask,
"task_args": {},
Expand Down
Original file line number Diff line number Diff line change
@@ -1,18 +1,13 @@
import os
import random
import re

from llmebench.datasets import AttentionworthyDataset
from llmebench.datasets import CT22AttentionworthyDataset
from llmebench.models import GPTChatCompletionModel
from llmebench.tasks import AttentionworthyTask


random.seed(1333)


def config():
return {
"dataset": AttentionworthyDataset,
"dataset": CT22AttentionworthyDataset,
"dataset_args": {},
"task": AttentionworthyTask,
"task_args": {},
Expand Down
Original file line number Diff line number Diff line change
@@ -1,13 +1,13 @@
import os

from llmebench.datasets import CheckworthinessDataset
from llmebench.datasets import CT22CheckworthinessDataset
from llmebench.models import BLOOMPetalModel
from llmebench.tasks import CheckworthinessTask


def config():
return {
"dataset": CheckworthinessDataset,
"dataset": CT22CheckworthinessDataset,
"dataset_args": {},
"task": CheckworthinessTask,
"task_args": {},
Expand Down
Original file line number Diff line number Diff line change
@@ -1,13 +1,13 @@
import os

from llmebench.datasets import CheckworthinessDataset
from llmebench.datasets import CT22CheckworthinessDataset
from llmebench.models import GPTModel, RandomGPTModel
from llmebench.tasks import CheckworthinessTask


def config():
return {
"dataset": CheckworthinessDataset,
"dataset": CT22CheckworthinessDataset,
"dataset_args": {},
"task": CheckworthinessTask,
"task_args": {},
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@
import random
import re

from llmebench.datasets import CheckworthinessDataset
from llmebench.datasets import CT22CheckworthinessDataset
from llmebench.models import GPTChatCompletionModel
from llmebench.tasks import CheckworthinessTask

Expand All @@ -12,7 +12,7 @@

def config():
return {
"dataset": CheckworthinessDataset,
"dataset": CT22CheckworthinessDataset,
"dataset_args": {},
"task": CheckworthinessTask,
"task_args": {},
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@
import random
import re

from llmebench.datasets import CheckworthinessDataset
from llmebench.datasets import CT22CheckworthinessDataset
from llmebench.models import GPTChatCompletionModel
from llmebench.tasks import CheckworthinessTask

Expand All @@ -12,7 +12,7 @@

def config():
return {
"dataset": CheckworthinessDataset,
"dataset": CT22CheckworthinessDataset,
"dataset_args": {},
"task": CheckworthinessTask,
"task_args": {},
Expand Down
Original file line number Diff line number Diff line change
@@ -1,13 +1,13 @@
import os

from llmebench.datasets import CovidClaimDataset
from llmebench.datasets import CT22ClaimDataset
from llmebench.models import BLOOMPetalModel
from llmebench.tasks import ClaimDetectionTask


def config():
return {
"dataset": CovidClaimDataset,
"dataset": CT22ClaimDataset,
"dataset_args": {},
"task": ClaimDetectionTask,
"task_args": {},
Expand Down
Original file line number Diff line number Diff line change
@@ -1,13 +1,13 @@
import os

from llmebench.datasets import CovidClaimDataset
from llmebench.datasets import CT22ClaimDataset
from llmebench.models import GPTModel
from llmebench.tasks import ClaimDetectionTask


def config():
return {
"dataset": CovidClaimDataset,
"dataset": CT22ClaimDataset,
"dataset_args": {},
"task": ClaimDetectionTask,
"task_args": {},
Expand Down
Original file line number Diff line number Diff line change
@@ -1,13 +1,13 @@
import os

from llmebench.datasets import CovidClaimDataset
from llmebench.datasets import CT22ClaimDataset
from llmebench.models import GPTChatCompletionModel
from llmebench.tasks import ClaimDetectionTask


def config():
return {
"dataset": CovidClaimDataset,
"dataset": CT22ClaimDataset,
"dataset_args": {},
"task": ClaimDetectionTask,
"task_args": {},
Expand Down
Original file line number Diff line number Diff line change
@@ -1,18 +1,13 @@
import os
import random
import re

from llmebench.datasets import CheckworthinessDataset
from llmebench.datasets import CT22CheckworthinessDataset
from llmebench.models import GPTChatCompletionModel
from llmebench.tasks import CheckworthinessTask


random.seed(1333)


def config():
return {
"dataset": CheckworthinessDataset,
"dataset": CT22CheckworthinessDataset,
"dataset_args": {},
"task": CheckworthinessTask,
"task_args": {},
Expand Down
Original file line number Diff line number Diff line change
@@ -1,15 +1,15 @@
import os

from llmebench.datasets import FactualityCOVID19Dataset
from llmebench.datasets import COVID19FactualityDataset
from llmebench.models import BLOOMPetalModel
from llmebench.tasks import FactualityCOVID19Task
from llmebench.tasks import FactualityTask


def config():
return {
"dataset": FactualityCOVID19Dataset,
"dataset": COVID19FactualityDataset,
"dataset_args": {},
"task": FactualityCOVID19Task,
"task": FactualityTask,
"task_args": {},
"model": BLOOMPetalModel,
"model_args": {
Expand Down
Original file line number Diff line number Diff line change
@@ -1,20 +1,15 @@
import os
import random
import re

from llmebench.datasets import FactualityCOVID19Dataset
from llmebench.datasets import COVID19FactualityDataset
from llmebench.models import GPTChatCompletionModel
from llmebench.tasks import FactualityCOVID19Task


random.seed(1333)
from llmebench.tasks import FactualityTask


def config():
return {
"dataset": FactualityCOVID19Dataset,
"dataset": COVID19FactualityDataset,
"dataset_args": {},
"task": FactualityCOVID19Task,
"task": FactualityTask,
"task_args": {},
"model": GPTChatCompletionModel,
"model_args": {
Expand Down
Original file line number Diff line number Diff line change
@@ -1,20 +1,15 @@
import os
import random
import re

from llmebench.datasets import FactualityCOVID19Dataset
from llmebench.datasets import COVID19FactualityDataset
from llmebench.models import GPTChatCompletionModel
from llmebench.tasks import FactualityCOVID19Task


random.seed(1333)
from llmebench.tasks import FactualityTask


def config():
return {
"dataset": FactualityCOVID19Dataset,
"dataset": COVID19FactualityDataset,
"dataset_args": {},
"task": FactualityCOVID19Task,
"task": FactualityTask,
"task_args": {},
"model": GPTChatCompletionModel,
"model_args": {
Expand Down
Original file line number Diff line number Diff line change
@@ -1,20 +1,15 @@
import os
import random
import re

from llmebench.datasets import FactualityKhouja20Dataset
from llmebench.datasets import Khouja20FactualityDataset
from llmebench.models import BLOOMPetalModel
from llmebench.tasks import FactualityKhouja20Task


random.seed(1333)
from llmebench.tasks import FactualityTask


def config():
return {
"dataset": FactualityKhouja20Dataset,
"dataset": Khouja20FactualityDataset,
"dataset_args": {},
"task": FactualityKhouja20Task,
"task": FactualityTask,
"task_args": {},
"model": BLOOMPetalModel,
"model_args": {
Expand Down
Original file line number Diff line number Diff line change
@@ -1,15 +1,15 @@
import os

from llmebench.datasets import FactualityKhouja20Dataset
from llmebench.models import GPTModel, RandomGPTModel
from llmebench.tasks import FactualityKhouja20Task
from llmebench.datasets import Khouja20FactualityDataset
from llmebench.models import GPTModel
from llmebench.tasks import FactualityTask


def config():
return {
"dataset": FactualityKhouja20Dataset,
"dataset": Khouja20FactualityDataset,
"dataset_args": {},
"task": FactualityKhouja20Task,
"task": FactualityTask,
"task_args": {},
"model": GPTModel,
"model_args": {
Expand Down
Original file line number Diff line number Diff line change
@@ -1,15 +1,15 @@
import os

from llmebench.datasets import FactualityKhouja20Dataset
from llmebench.datasets import Khouja20FactualityDataset
from llmebench.models import GPTChatCompletionModel
from llmebench.tasks import FactualityKhouja20Task
from llmebench.tasks import FactualityTask


def config():
return {
"dataset": FactualityKhouja20Dataset,
"dataset": Khouja20FactualityDataset,
"dataset_args": {},
"task": FactualityKhouja20Task,
"task": FactualityTask,
"task_args": {},
"model": GPTChatCompletionModel,
"model_args": {
Expand Down
Original file line number Diff line number Diff line change
@@ -1,15 +1,15 @@
import os

from llmebench.datasets import FactualityKhouja20Dataset
from llmebench.datasets import Khouja20FactualityDataset
from llmebench.models import GPTChatCompletionModel
from llmebench.tasks import FactualityKhouja20Task
from llmebench.tasks import FactualityTask


def config():
return {
"dataset": FactualityKhouja20Dataset,
"dataset": Khouja20FactualityDataset,
"dataset_args": {},
"task": FactualityKhouja20Task,
"task": FactualityTask,
"task_args": {},
"model": GPTChatCompletionModel,
"model_args": {
Expand Down
Original file line number Diff line number Diff line change
@@ -1,20 +1,15 @@
import os
import random
import re

from llmebench.datasets import FactualityUnifiedFCDataset
from llmebench.datasets import UnifiedFCFactualityDataset
from llmebench.models import BLOOMPetalModel
from llmebench.tasks import FactualityUnifiedFCTask


random.seed(1333)
from llmebench.tasks import FactualityTask


def config():
return {
"dataset": FactualityUnifiedFCDataset,
"dataset": UnifiedFCFactualityDataset,
"dataset_args": {},
"task": FactualityUnifiedFCTask,
"task": FactualityTask,
"task_args": {},
"model": BLOOMPetalModel,
"model_args": {
Expand Down
Loading