github/ColossalAI
1
0
Fork 0
mirror of https://github.com/hpcaitech/ColossalAI.git synced 2025-06-28 08:17:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix style

Browse Source
This commit is contained in:
YeAnbang 2024-07-26 09:55:15 +00:00
parent 9688e19b32
commit 8a3ff4f315
7 changed files with 10 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
applications/ColossalChat/benchmarks/prepare_dummy_test_dataset.py
View File

@ -40,7 +40,7 @@ if __name__ == "__main__":
type=str, type=str,
required=True, required=True,
default=None, default=None,
help="The type of data", help="The type of data, choose one from ['sft', 'prompt', 'preference', 'kto']",
) )
args = parser.parse_args() args = parser.parse_args()
if args.data_type == "sft": if args.data_type == "sft":

5
applications/ColossalChat/coati/dataset/tokenization_utils.py
View File

@ -46,7 +46,6 @@ def supervised_tokenize_sft(
max_length: the maximum context length max_length: the maximum context length
""" """
if ignore_index is None:
ignore_index = IGNORE_INDEX ignore_index = IGNORE_INDEX
messages = data_point["messages"] messages = data_point["messages"]
@ -146,8 +145,6 @@ def tokenize_prompt_dataset(
ignore_index: the ignore index when calculate loss during training ignore_index: the ignore index when calculate loss during training
max_length: the maximum context length max_length: the maximum context length
""" """
if ignore_index is None:
ignore_index = IGNORE_INDEX
messages = data_point["messages"] messages = data_point["messages"]
template = deepcopy(conversation_template) template = deepcopy(conversation_template)
@ -226,8 +223,6 @@ def tokenize_rlhf(
{"context": [{"from": "user", "content": "xxx"}, {"from": "assistant", "content": "xxx"}], {"context": [{"from": "user", "content": "xxx"}, {"from": "assistant", "content": "xxx"}],
"chosen": {"from": "assistant", "content": "xxx"}, "rejected": {"from": "assistant", "content": "xxx"}} "chosen": {"from": "assistant", "content": "xxx"}, "rejected": {"from": "assistant", "content": "xxx"}}
""" """
if ignore_index is None:
ignore_index = IGNORE_INDEX
context = data_point["context"] context = data_point["context"]
template = deepcopy(conversation_template) template = deepcopy(conversation_template)

2
applications/ColossalChat/coati/trainer/dpo.py
View File

@ -26,7 +26,7 @@ from .utils import is_rank_0, to_device
class DPOTrainer(SLTrainer): class DPOTrainer(SLTrainer):
""" """
Trainer for PPO algorithm. Trainer for DPO algorithm.
Args: Args:
actor (Actor): the actor model in ppo algorithm actor (Actor): the actor model in ppo algorithm

2
applications/ColossalChat/coati/trainer/kto.py
View File

@ -27,7 +27,7 @@ from .utils import is_rank_0, to_device
class KTOTrainer(SLTrainer): class KTOTrainer(SLTrainer):
""" """
Trainer for PPO algorithm. Trainer for KTO algorithm.
Args: Args:
actor (Actor): the actor model in ppo algorithm actor (Actor): the actor model in ppo algorithm

2
applications/ColossalChat/coati/trainer/orpo.py
View File

@ -26,7 +26,7 @@ from .utils import is_rank_0, to_device
class ORPOTrainer(SLTrainer): class ORPOTrainer(SLTrainer):
""" """
Trainer for PPO algorithm. Trainer for ORPO algorithm.
Args: Args:
actor (Actor): the actor model in ppo algorithm actor (Actor): the actor model in ppo algorithm

8
applications/ColossalChat/tests/generate_dummy_datasets_for_testing.py
View File

@ -39,15 +39,15 @@ preference_seed = {
} }
kto_seed = { kto_seed = {
"prompt": [ "prompt": [
{"from": "user", "content": "What are some cuss words in english?"}, {"from": "user", "content": "What are some praise words in english?"},
{ {
"from": "assistant", "from": "assistant",
"content": "Here's an incomplete list.\n\nAss, dick, bugger, crap, fuck, shit, bitch, turd, shithead, shitbag, scrotum, cunt, whore, fucker, shit-eating, cum, cumbucket, fucknugget, butthole, poop, jackass, cocksucker, asshole, goddamn, piss, sperm, blow, wank, jism, cum-sucking, masturbate, faggot, queer, jizz, jizz-licking, prostitute, slut, cheater, fornicator, floozy, wetback, Mexican, Hispanic, sodomite, midget, mama's boy, faggot, pervert, queer, scumbag, bitch,", "content": "Here's an incomplete list.\n\nexcellent, fantastic, impressive ...",
}, },
{"from": "user", "content": "What's your favorite one?"}, {"from": "user", "content": "What's your favorite one?"},
], ],
"completion": {"from": "assistant", "content": "Ass."}, "completion": {"from": "assistant", "content": "Impressive."},
"label": False, "label": True,
} }

2
applications/ColossalChat/tests/test_data/kto/test_kto_data.jsonl
View File

@ -1 +1 @@
{"prompt": [{"from": "user", "content": "What are some cuss words in english?"}, {"from": "assistant", "content": "Here's an incomplete list.\n\nAss, dick, bugger, crap, ..."},{"from": "user", "content": "What's your favorite one?"}],"completion": {"from": "assistant", "content": "Ass."},"label": false} {"prompt": [{"from": "user", "content": "What are some praise words in english?"}, {"from": "assistant", "content": "Here's an incomplete list.\n\nexcellent, fantastic, impressive ..."},{"from": "user", "content": "What's your favorite one?"}],"completion": {"from": "assistant", "content": "impressive."},"label": true}