Add files via upload

openseek/competition/LongContext-ICL-Annotation/src/main.py

@@ -6,18 +6,18 @@
 
 from method import build_prompt, select_examples
 
-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',
 }
 
 def parser_args():
@@ -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
 
@@ -48,16 +48,14 @@ 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
-    output_file = f'{log_path_prefix}openseek-{task_id}-v{version}.jsonl'
+    # The evaluation platform currently expects the submission filename to be
+    # exactly openseek-{task_id}-v1.jsonl.
+    output_file = f'{log_path_prefix}openseek-{task_id}-v1.jsonl'
     output_path = os.path.dirname(output_file)
     os.makedirs(output_path, exist_ok=True)
-    while os.path.exists(output_file):
-        version += 1
-        output_file = f'{log_path_prefix}openseek-{task_id}-v{version}.jsonl'
     with open(output_file, 'w') as f:
         pass
 
@@ -79,14 +77,14 @@ def evaluate(task_id:int,
         # 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')
 
 if __name__ == '__main__':
     args = parser_args()
     qwen_tokenizer = AutoTokenizer.from_pretrained(args.tokenizer_path)
-    evaluate(args.task_id, qwen_tokenizer, args.max_input_length, args.log_path_prefix)
+    evaluate(args.task_id, qwen_tokenizer, args.max_input_length, args.log_path_prefix)

openseek/competition/LongContext-ICL-Annotation/src/method.py

@@ -158,7 +158,7 @@ def select_examples(all_examples: list[dict], task_description: str, text2annota
     """
     # 初始化Qwen3-4B的tokenizer（自动下载/加载千问3-4B的分词器）
     # 若本地已下载模型，可替换为本地路径，如 "./qwen3-4b"
-    tokenizer = AutoTokenizer.from_pretrained("/share/project/wuhaiming/spaces/data_agent/OpenSeek-main/openseek/competition/LongContext-ICL-Annotation/src/Qwen3-4B", trust_remote_code=True)
+    tokenizer = AutoTokenizer.from_pretrained("/root/Qwen3-4B", trust_remote_code=True)
 
     # 最大上下文长度限制（Qwen3-4B的上下文窗口默认是8k/32k，可根据实际调整）
     target_length = 8192  # 若需严格适配Qwen3-4B，建议改为8192（8k）
@@ -217,8 +217,6 @@ def count_answer(text: str) -> tuple[list, dict]:
     max_count = max(content_counter.values())
     answer = [content for content, count in content_counter.items() if count == max_count]
 
-    if (len(answer[0]) >= 100):
-        return None
     return answer[0]
 
 
@@ -235,7 +233,7 @@ def annotate_nvidia(input_prompt:str)->list[str]:
     data = {
         "model": "../Qwen3-4B",
         "prompt": input_prompt,
-        "max_tokens": 10_000, # max_token = 10k
+        "max_tokens": 1024, # max_token = 10k
     }
 
     try:
@@ -248,7 +246,7 @@ def annotate_nvidia(input_prompt:str)->list[str]:
     prediction = count_answer(whole_result)
     return prediction
 
-def annotate_ascend(input_prompt:str)->list[str]:
+def annotate_ascend(input_prompt:str, task_id:int=None)->list[str]:
     """
         Annotate the unlabeled data using an LLM API (Huawei Ascend).
         prompts:
@@ -258,7 +256,7 @@ def annotate_ascend(input_prompt:str)->list[str]:
     import openai
     openai.api_key = "EMPTY"
     openai.base_url = "http://localhost:9010/v1/"
-    model = "Qwen3-4B-ascend-flagos"
+    model = "/root/Qwen3-4B"
 
     messages = [
         {"role": "system", "content": "You are a helpful assistant."},
@@ -269,9 +267,16 @@ def annotate_ascend(input_prompt:str)->list[str]:
         messages=messages,
         temperature=0.7,
         top_p=0.95,
-        max_tokens=10_000,
+        max_tokens=1024,
         stream=False,
     )
     whole_result = response.choices[0].message.content
+
+    # Special handling for Task 8 (code generation): return raw model output
+    # Task 8 generates Triton code without <label> tags
+    if task_id == 8:
+        return whole_result.strip()
+
+    # For other tasks, extract label-tagged content
     prediction = count_answer(whole_result)
     return prediction

openseek/competition/LongContext-ICL-Annotation/src/requirements.txt

@@ -0,0 +1,17 @@
+# Python依赖环境配置
+# 适用于 Huawei Ascend 910C 环境
+
+# 基础依赖
+numpy>=1.24.0
+torch>=2.8.0
+torch_npu>=2.8.0
+torchvision>=0.23.0
+
+# 模型与推理
+transformers>=4.57.0
+vllm_ascend>=0.13.0rc1
+
+# 工具库
+tqdm>=4.67.0
+requests>=2.32.0
+openai>=2.14.0