github/ColossalAI
1
0
Fork 0
mirror of https://github.com/hpcaitech/ColossalAI.git synced 2025-09-04 10:34:41 +00:00
Code Issues Packages Projects Releases Wiki Activity

[feat] Dist Loader for Eval (#5950)

Browse Source 
* support auto distributed data loader

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* support auto distributed data loader

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* fix tp error

* remove unused parameters

* remove unused

* update inference

* update docs

* update inference

---------

Co-authored-by: Michelle <qianranma8@gmail.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
This commit is contained in:
Tong Li
2024-08-02 10:06:25 +08:00
committed by GitHub
parent 62cdac6b7b
commit 19d1510ea2
15 changed files with 93 additions and 77 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
applications/ColossalEval/colossal_eval/utils/conversation.py
View File

@@ -123,15 +123,13 @@ class Conversation:
}
def get_few_shot_prefix(
conv: Conversation, few_shot_data: List[str], tokenizer: Optional[AutoTokenizer], language: str, max_tokens: int
) -> str:
def get_few_shot_prefix(few_shot_data: List[str], tokenizer: Optional[AutoTokenizer], max_tokens: int) -> str:
"""
Get few shot prefix.
Args:
conv: Conversation template.
few_shot_examples: Few shot examples to generate few shot prompt prefix.
few_shot_data: Few shot examples to generate few shot prompt prefix.
tokenizer: tokenizer used to tokenize data.
Returns:
Few shot prompt prefix.
@@ -157,7 +155,6 @@ def get_batch_prompt(
batch: List[Dict],
few_shot_data: List[str],
tokenizer: Optional[AutoTokenizer],
language: Optional[str],
model_max_length: Optional[int],
) -> Tuple[List[Dict], List[Dict]]:
"""
@@ -167,6 +164,7 @@ def get_batch_prompt(
conv: Conversation template.
batch: Batch data to generate prompt from.
few_shot_data: Few shot data to generate few shot prompt prefix.
tokenizer: tokenizer used to tokenize data.
Returns:
Tuple containg batch prompt and target.
@@ -192,7 +190,7 @@ def get_batch_prompt(
else:
raise Exception("When using few-shot, target answer should be a string.")
few_shot_prefix = get_few_shot_prefix(conv, few_shot_data, tokenizer, language, max_tokens)
few_shot_prefix = get_few_shot_prefix(few_shot_data, tokenizer, max_tokens)
conv.append_message(conv.roles[0], few_shot_prefix + query_text)
conv.append_message(conv.roles[1], None)