Functions — github.com/deepseek-ai/DeepSeek-Coder

hub / github.com/deepseek-ai/DeepSeek-Coder / functions

Functions149 in github.com/deepseek-ai/DeepSeek-Coder

⨍ Functions 149◇ Types & classes 23

↓ 1 callersFunctiontrain

()

finetune/finetune_deepseekcoder.py:121

Method__call__

(self, instances: Sequence[Dict])

finetune/finetune_deepseekcoder.py:97

Method__call__

(self, input_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs)

Evaluation/MBPP/mbpp.py:25

Method__getitem__

(self, index)

Evaluation/MBPP/utils/dataset.py:45

Method__getitem__

return the sample at index

Evaluation/HumanEval/utils/dataset.py:56

Method__init__

(self, keywords_str, tokenizer)

Evaluation/MBPP/mbpp.py:20

Method__init__

root: 数据文件的根目录

Evaluation/MBPP/utils/dataset.py:7

Method__init__

(self)

Evaluation/PAL-Math/utils/python_executor.py:27

Method__init__

( self, runtime: Optional[Any] = None, get_answer_symbol: Optional[str] = None,

Evaluation/PAL-Math/utils/python_executor.py:67

Method__init__

(self, data_root, max_seq_len=2048, language="python", max_gen_len=200, batch_size=512,

Evaluation/HumanEval/humaneval.py:22

Method__init__

root: the path to the HumanEval dataset sample_num: the number of samples for each prompt language: the language of the Human

Evaluation/HumanEval/utils/dataset.py:7

Method__iter__

(self)

Evaluation/PAL-Math/utils/python_executor.py:59

Method__len__

(self)

Evaluation/MBPP/utils/dataset.py:42

Method__len__

return the number of samples in the dataset

Evaluation/HumanEval/utils/dataset.py:50

Methodanswer

(self)

Evaluation/PAL-Math/utils/python_executor.py:47

Functioncheck_correctness

Evaluates the functional correctness of a completion by running the test suite provided in the problem.

Evaluation/MBPP/human_eval/execution.py:23

Functioncheck_correctness

Evaluates the functional correctness of a completion by running the test suite provided in the problem.

Evaluation/LeetCode/human_eval/execution.py:23

Functioncheck_correctness

Evaluates the functional correctness of a completion by running the test suite provided in the problem.

Evaluation/HumanEval/human_eval/execution.py:23

Functioncleanup_code

Cleans up the generated code.

Evaluation/MBPP/utils/utils.py:1

Functionentry_point

Evaluates the functional correctness of generated samples, and writes results to f"{sample_file}_results.jsonl.gz"

Evaluation/MBPP/human_eval/evaluate_functional_correctness.py:8

Functionentry_point

Evaluates the functional correctness of generated samples, and writes results to f"{sample_file}_results.jsonl.gz"

Evaluation/HumanEval/human_eval/evaluate_functional_correctness.py:8

Methodeval_code

(self, expr: str)

Evaluation/PAL-Math/utils/python_executor.py:39

Functionevaluation_only

(args)

Evaluation/HumanEval/eval_instruct.py:91

Methodexecute

( code, get_answer_from_stdout = None, runtime = None, answer_symbol = None,

Evaluation/PAL-Math/utils/python_executor.py:85

Functiongenerate

( message: str, chat_history: list, system_prompt: str, max_new_tokens: int = 1024, temper

demo/app.py:34

Methodinject

(self, var_dict: Dict[str, Any])

Evaluation/PAL-Math/utils/python_executor.py:42

Functionmath_equal_process

(param)

Evaluation/PAL-Math/utils/grader.py:95

Methodread

(self, *args, **kwargs)

Evaluation/LeetCode/human_eval/execution.py:626

Functionread_problems

(evalset_file: str = HUMAN_EVAL)

Evaluation/MBPP/human_eval/data.py:11

Functionread_problems

(evalset_file: str = HUMAN_EVAL)

Evaluation/LeetCode/human_eval/data.py:11

Functionread_problems

(evalset_file: str = HUMAN_EVAL)

Evaluation/HumanEval/human_eval/data.py:11

Methodreadable

Returns True if the IO object can be read.

Evaluation/MBPP/human_eval/execution.py:635

Methodreadable

Returns True if the IO object can be read.

Evaluation/LeetCode/human_eval/execution.py:635

Methodreadable

Returns True if the IO object can be read.

Evaluation/HumanEval/human_eval/execution.py:635

Methodreadline

(self, *args, **kwargs)

Evaluation/MBPP/human_eval/execution.py:629

Methodreadline

(self, *args, **kwargs)

Evaluation/LeetCode/human_eval/execution.py:629

Methodreadline

(self, *args, **kwargs)

Evaluation/HumanEval/human_eval/execution.py:629

Functionrun_execute

(executor, result, prompt_type, execute=False)

Evaluation/PAL-Math/utils/parser.py:306

Functionsignal_handler

(signum, frame)

Evaluation/MBPP/human_eval/execution.py:592

Functionsignal_handler

(signum, frame)

Evaluation/LeetCode/human_eval/execution.py:592

Functionsignal_handler

(signum, frame)

Evaluation/HumanEval/human_eval/execution.py:592

Functionsymbolic_equal_process

(a, b, output_queue)

Evaluation/PAL-Math/utils/grader.py:125

Functiontrain_tokenize_function

(examples, tokenizer)

finetune/finetune_deepseekcoder.py:112

Functionunsafe_execute

(tmp_dir)

Evaluation/MBPP/human_eval/execution.py:36

Functionunsafe_execute

(tmp_dir)

Evaluation/LeetCode/human_eval/execution.py:36

Functionunsafe_execute

(tmp_dir)

Evaluation/HumanEval/human_eval/execution.py:36

Functionwrite_jsonl

Writes an iterable of dictionaries to jsonl

Evaluation/MBPP/human_eval/data.py:32

Functionwrite_jsonl

Writes an iterable of dictionaries to jsonl

Evaluation/LeetCode/human_eval/data.py:32

Functionwrite_jsonl

Writes an iterable of dictionaries to jsonl

Evaluation/HumanEval/human_eval/data.py:32

← previous101–149 of 149, ranked by callers