Skip to content

Add files via upload #254

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.

Sign up for GitHub

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

Open
rubhudegaar wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Add files via upload #254

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
41 changes: 23 additions & 18 deletions openseek/competition/LongContext-ICL-Annotation/src/main.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,20 +4,20 @@

# from method import build_prompt, select_examples, annotate

from method import build_prompt, select_examples
from method import build_prompt, select_examples, select_examples_M05, select_examples_M19, select_examples_M20, build_prompt_cot, build_prompt_by_task_type

from method import annotate_nvidia as annotate # For Nvidia GPU
# from method import annotate_ascend as annotate # For Huawei Ascend
# from method import annotate_nvidia as annotate # For Nvidia GPU
from method import annotate_ascend as annotate # For Huawei Ascend

TASK_FILES = {
1: './data/openseek-1_closest_integers.json',
2: './data/openseek-2_count_nouns_verbs.json',
3: './data/openseek-3_collatz_conjecture.json',
4: './data/openseek-4_conala_concat_strings.json',
5: './data/openseek-5_semeval_2018_task1_tweet_sadness_detection.json',
6: './data/openseek-6_mnli_same_genre_classification.json',
7: './data/openseek-7_jeopardy_answer_generation_all.json',
8: '../data/openseek-8_kernel_generation.json',
1: '/root/OpenSeek/openseek/competition/LongContext-ICL-Annotation/data/openseek-1_closest_integers.json',
2: '/root/OpenSeek/openseek/competition/LongContext-ICL-Annotation/data/openseek-2_count_nouns_verbs.json',
3: '/root/OpenSeek/openseek/competition/LongContext-ICL-Annotation/data/openseek-3_collatz_conjecture.json',
4: '/root/OpenSeek/openseek/competition/LongContext-ICL-Annotation/data/openseek-4_conala_concat_strings.json',
5: '/root/OpenSeek/openseek/competition/LongContext-ICL-Annotation/data/openseek-5_semeval_2018_task1_tweet_sadness_detection.json',
6: '/root/OpenSeek/openseek/competition/LongContext-ICL-Annotation/data/openseek-6_mnli_same_genre_classification.json',
7: '/root/OpenSeek/openseek/competition/LongContext-ICL-Annotation/data/openseek-7_jeopardy_answer_generation_all.json',
8: '/root/OpenSeek/openseek/competition/LongContext-ICL-Annotation/data/openseek-8_kernel_generation.json',
}
Comment on lines 12 to 21

@gemini-code-assist gemini-code-assist Bot May 29, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

Hardcoding absolute paths like /root/OpenSeek/... makes the code non-portable and prone to failure when run in different environments or by other users. It is highly recommended to construct these paths dynamically relative to the script's location using os.path.

SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
DATA_DIR = os.path.join(os.path.dirname(SCRIPT_DIR), 'data')

TASK_FILES = {
    1: os.path.join(DATA_DIR, 'openseek-1_closest_integers.json'),
    2: os.path.join(DATA_DIR, 'openseek-2_count_nouns_verbs.json'),
    3: os.path.join(DATA_DIR, 'openseek-3_collatz_conjecture.json'),
    4: os.path.join(DATA_DIR, 'openseek-4_conala_concat_strings.json'),
    5: os.path.join(DATA_DIR, 'openseek-5_semeval_2018_task1_tweet_sadness_detection.json'),
    6: os.path.join(DATA_DIR, 'openseek-6_mnli_same_genre_classification.json'),
    7: os.path.join(DATA_DIR, 'openseek-7_jeopardy_answer_generation_all.json'),
    8: os.path.join(DATA_DIR, 'openseek-8_kernel_generation.json'),
}


def parser_args():
Expand All @@ -30,7 +30,7 @@ def parser_args():
default='../outputs/',
help='Prefix path to save the evaluation logs.')
parser.add_argument('--tokenizer_path', type=str,
default='/share/project/wuhaiming/spaces/data_agent/OpenSeek-main/openseek/competition/LongContext-ICL-Annotation/src/Qwen3-4B')
default='/root/Qwen3-4B')
args = parser.parse_args()
return args

Expand All @@ -48,7 +48,7 @@ def evaluate(task_id:int,

task_name = task_dict['task_name']
task_description = task_dict['Definition'][0]
icl_examples = task_dict['examples'][:100]
icl_examples = task_dict['examples'][:50]
test_samples = task_dict['test_samples']

version = 1
Expand All @@ -62,26 +62,31 @@ def evaluate(task_id:int,
pass

examples_str = None
for test_sample in tqdm(test_samples, desc=f'Evaluation on Task {task_id}: {task_name}'):
for sample_idx, test_sample in enumerate(tqdm(test_samples, desc=f'Evaluation on Task {task_id}: {task_name}')):
test_record = dict()

test_sample_id = test_sample['id']
test_record['test_sample_id'] = test_sample_id


text2annotate = test_sample['input']
prompt = build_prompt(task_description, text2annotate)

# M03优化：使用任务分型Prompt路由系统
# 根据任务类型自动选择最合适的prompt策略
prompt = build_prompt_by_task_type(task_id, task_description, text2annotate)

if examples_str is None:
examples_str = select_examples(icl_examples, task_description, text2annotate)
# M19优化：使用检索+重试+后处理组合策略
examples_str = select_examples_M19(icl_examples, task_description, text2annotate, task_id, sample_idx)
Comment on lines 78 to +80

@gemini-code-assist gemini-code-assist Bot May 29, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

high

The newly introduced select_examples_M19 is a dynamic retrieval strategy that selects few-shot examples based on similarity to the current sample's input (text2annotate). However, because examples_str is defined outside the loop and guarded by if examples_str is None:, it is only computed once for the first sample and then reused for all subsequent samples. This completely defeats the purpose of dynamic retrieval.

To fix this, you should remove the if examples_str is None: check so that the examples are dynamically retrieved for each sample.

        # M19优化：使用检索+重试+后处理组合策略
        examples_str = select_examples_M19(icl_examples, task_description, text2annotate, task_id, sample_idx)

input_prompt = prompt.replace("[[EXAMPLES]]\n\n", examples_str+'\n\n')

# tokenized_input = qwen_tokenizer(input_prompt, return_tensors="pt")
# if tokenized_input['input_ids'].shape[1] > max_input_length:
# test_record['prediction'] = None
# else:
# prediction = annotate(input_prompt)
# prediction = annotate(input_prompt, task_id)
# test_record['prediction'] = prediction
prediction = annotate(input_prompt)
prediction = annotate(input_prompt, task_id)
test_record['prediction'] = prediction
with open(output_file, 'a') as f:
f.write(json.dumps(test_record)+'\n')
Expand Down
Loading