MCPcopy Create free account

hub / github.com/SkyworkAI/Skywork / functions

Functions50 in github.com/SkyworkAI/Skywork

⨍ Functions 50◇ Types & classes 5
↓ 5 callersFunctionset_seed
Helper function for reproducible behavior to set the seed in `random`, `numpy`, `torch` and/or `tf` (if installed). Args: seed (`int
eval/eval_loss.py:122
↓ 2 callersFunctionextract_res
(response)
skywork_chat_demo.py:35
↓ 2 callersFunctionformat_example
(line, subject, include_answer=True)
eval/evaluate_cmmlu.py:111
↓ 2 callersFunctionformat_example
(line, subject, include_answer=True)
eval/evaluate_ceval.py:90
↓ 2 callersFunctionformat_example
(line, include_answer=True)
eval/evaluate_mmlu.py:36
↓ 2 callersFunctionget_match_str
(match, idx)
eval/eval_gsm8k.py:24
↓ 2 callersFunctionspecial_encode
(prompt, tokenizer)
skywork_chat_demo.py:46
↓ 1 callersFunctionbuild_instruction_dataset
(data_path: Union[List[str],str], tokenizer: transformers.PreTrainedTokenizer,
train/build_dataset.py:21
↓ 1 callersFunctioncal_ceval
(res)
eval/evaluate_ceval.py:213
↓ 1 callersFunctioncal_cmmlu
(res)
eval/evaluate_cmmlu.py:233
↓ 1 callersFunctioncal_mmlu
(res)
eval/evaluate_mmlu.py:162
↓ 1 callersFunctioncompute_loss
(tokenized_texts, attention_mask, model, tokenizer, add_start_token=False)
eval/eval_loss.py:32
↓ 1 callersFunctiondecode
(tokens_list, tokenizer, raw_text_len)
eval/eval_gsm8k.py:44
↓ 1 callersFunctiondoc_to_text
(doc)
eval/eval_gsm8k.py:35
↓ 1 callersFunctioneval_subject
( model, tokenizer, subject_name, test_df, k=5, dev_df=None, few_shot=False, s
eval/evaluate_cmmlu.py:149
↓ 1 callersFunctioneval_subject
( model, tokenizer, subject_name, test_df, k=5, dev_df=None, few_shot=False, s
eval/evaluate_ceval.py:128
↓ 1 callersFunctioneval_subject
( model, tokenizer, subject_name, test_df, k=5, dev_df=None, few_shot=False, s
eval/evaluate_mmlu.py:85
↓ 1 callersFunctionextract_answer
(text)
eval/eval_gsm8k.py:74
↓ 1 callersFunctionextract_answer_hf
(completion)
eval/eval_gsm8k.py:65
↓ 1 callersFunctionextract_res
(response)
cli_demo.py:54
↓ 1 callersFunctionformat_subject
(subject)
eval/evaluate_mmlu.py:49
↓ 1 callersFunctiongenerate_few_shot_prompt
(k, subject, dev_df)
eval/evaluate_cmmlu.py:124
↓ 1 callersFunctiongenerate_few_shot_prompt
(k, subject, dev_df)
eval/evaluate_ceval.py:103
↓ 1 callersFunctiongenerate_few_shot_prompt
(k, subject, dev_df)
eval/evaluate_mmlu.py:48
↓ 1 callersFunctiongenerate_sample
(model, tokenizer, input_txt)
eval/eval_gsm8k.py:54
↓ 1 callersFunctionget_logits
(tokenizer, model, inputs: List[str])
eval/evaluate_cmmlu.py:137
↓ 1 callersFunctionget_logits
(tokenizer, model, inputs: List[str])
eval/evaluate_ceval.py:116
↓ 1 callersFunctionget_logits
(tokenizer, model, inputs: List[str])
eval/evaluate_mmlu.py:70
↓ 1 callersFunctionget_peft_state_maybe_zero_3
(named_params, bias)
train/train.py:178
↓ 1 callersFunctionis_correct
(completion, answer)
eval/eval_gsm8k.py:93
↓ 1 callersFunctionload
(tokenizer_path, checkpoint_path, use_cpu=False)
cli_demo.py:8
↓ 1 callersFunctionload
(tokenizer_path, checkpoint_path)
skywork_chat_demo.py:7
↓ 1 callersFunctionload_model_tokenizer_config
()
eval/eval_loss.py:60
↓ 1 callersFunctionload_models_tokenizer
(args)
eval/evaluate_cmmlu.py:95
↓ 1 callersFunctionload_models_tokenizer
(args)
eval/evaluate_ceval.py:77
↓ 1 callersFunctionload_models_tokenizer
(args)
eval/evaluate_mmlu.py:23
↓ 1 callersFunctionmain
(args)
eval/evaluate_cmmlu.py:350
↓ 1 callersFunctionmain
(args)
eval/evaluate_ceval.py:439
↓ 1 callersFunctionmain
(args)
eval/evaluate_mmlu.py:190
↓ 1 callersFunctionmain
()
eval/eval_loss.py:71
↓ 1 callersFunctionmain
()
train/train.py:221
↓ 1 callersFunctionmain
(args)
train/pt_data_preprocess.py:23
↓ 1 callersFunctionsafe_save_model_for_hf_trainer
Collects the state dict and dump to disk.
train/train.py:203
↓ 1 callersFunctionspecial_encode
(prompt, tokenizer)
cli_demo.py:39
Method__call__
(self, instances: Sequence[Dict])
train/build_dataset.py:95
Method__post_init__
(self)
train/train.py:122
Functionfault_tolerance_data_collator
(features: List)
train/build_dataset.py:108
Functiongroup_texts
(examples)
train/pt_data_preprocess.py:33
Functiontokenization
(examples)
train/build_dataset.py:27
Functiontokenize_function
(examples)
train/pt_data_preprocess.py:27