MCPcopy Create free account

hub / github.com/RUCAIBox/LLMSurvey / functions

Functions1,088 in github.com/RUCAIBox/LLMSurvey

⨍ Functions 1,088◇ Types & classes 151↳ Endpoints 1
↓ 74 callersMethodload
(self)
Experiments/InstructTuning/mmlu/modeling.py:287
↓ 68 callersMethodwrite
(self)
Experiments/ToolManipulation/HotPotQA/wrappers.py:233
↓ 50 callersFunctiontree_to_variable_index
(root_node,index_to_code)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/utils.py:76
↓ 18 callersFunctioncommaSep1
(rule)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/grammar.js:1058
↓ 17 callersMethodclose
(self)
Experiments/ToolManipulation/HotPotQA/wrappers.py:239
↓ 8 callersFunctionnormalize_answer
(s)
Experiments/ToolManipulation/HotPotQA/wrappers.py:42
↓ 6 callersFunctionngrams
Return the ngrams generated from a sequence of items, as an iterator. For example: >>> from nltk.util import ngrams >>> l
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/utils.py:51
↓ 6 callersMethodprocess_single_data
(self, data)
Experiments/SymbolicReasoning/data_process.py:247
↓ 6 callersMethodprocess_single_data
(self, data)
Experiments/MathematicalReasoning/data_process.py:247
↓ 6 callersFunctionremove_comments_and_docstrings
(source,lang)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/utils.py:8
↓ 5 callersMethodprocess_single_data
(self, data)
Experiments/SymbolicReasoning/data_process.py:95
↓ 5 callersMethodprocess_single_data
(self, data)
Experiments/MathematicalReasoning/data_process.py:95
↓ 4 callersMethod__init__
( self, name: str, batch_size: int = 1, temperature: float = 0.8,
Experiments/LanguageGeneration/HumanEval/model.py:76
↓ 4 callersFunctionannotate
(prompt, logit_bias=None)
Experiments/HumanAlignment/model/ChatGPT.py:74
↓ 4 callersFunctionfind_denominator
(text)
Experiments/MathematicalReasoning/evaluate_falcon.py:183
↓ 4 callersFunctionfind_denominator
(text)
Experiments/MathematicalReasoning/evaluate.py:182
↓ 4 callersFunctionfind_nominator
(text)
Experiments/MathematicalReasoning/evaluate_falcon.py:179
↓ 4 callersFunctionfind_nominator
(text)
Experiments/MathematicalReasoning/evaluate.py:178
↓ 4 callersFunctionnormalize_text
Lower text and remove punctuation, articles and extra whitespace. Copied from the [QuAC](http://quac.ai/) evaluation script found at https://s
Experiments/KnowledgeUtilization/WikiFact/em.py:7
↓ 4 callersMethodprocess
( self, data, num_del_examplar=0, pattern_demo="Problem: {}\nS
Experiments/SymbolicReasoning/data_process.py:17
↓ 4 callersMethodprocess
( self, data, num_del_examplar=0, pattern_demo="Problem: {}\nS
Experiments/MathematicalReasoning/data_process.py:17
↓ 4 callersMethodreset
(self, seed=None, return_info=False, options=None)
Experiments/ToolManipulation/HotPotQA/wikienv.py:47
↓ 4 callersMethodstep
(self, action)
Experiments/ToolManipulation/HotPotQA/wikienv.py:144
↓ 4 callersMethodstep
(self, action)
Experiments/ToolManipulation/HotPotQA/wrappers.py:186
↓ 3 callersMethod__init__
(self, env, split)
Experiments/ToolManipulation/HotPotQA/wrappers.py:140
↓ 3 callersMethod_get_info
(self)
Experiments/ToolManipulation/HotPotQA/wikienv.py:44
↓ 3 callersFunctionget_answer_boxed
(content)
Experiments/MathematicalReasoning/do_math.py:348
↓ 3 callersFunctionget_categories
()
Experiments/InstructTuning/mmlu/mmlu.py:86
↓ 3 callersFunctionget_choices
()
Experiments/InstructTuning/mmlu/mmlu.py:20
↓ 3 callersFunctionmodified_precision
Calculate modified ngram precision. The normal precision method may lead to some wrong translations with high-precision, e.g., the tra
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/bleu.py:205
↓ 3 callersFunctionnum_tokens_from_message
(message, model="davinci")
Experiments/HumanAlignment/HaluEval/openai_gpt.py:11
↓ 3 callersMethodreset
(self, seed=None, return_info=False, options=None, idx=None)
Experiments/ToolManipulation/HotPotQA/wrappers.py:158
↓ 3 callersFunctionsep1
(rule, separator)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/grammar.js:1062
↓ 3 callersMethodsum
()
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/examples/python3.8_grammar.py:1501
↓ 3 callersFunctiontest_equal
(equ1, equ2)
Experiments/MathematicalReasoning/evaluate_falcon.py:63
↓ 3 callersFunctiontest_equal
(equ1, equ2)
Experiments/MathematicalReasoning/evaluate.py:63
↓ 3 callersMethodwrite
(self, msg)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/examples/python2-grammar.py:322
↓ 2 callersMethod_find_gen_func_sig
(prompt)
Experiments/LanguageGeneration/HumanEval/model.py:270
↓ 2 callersMethod_quantize
(self, x, scale, zero, maxq)
Experiments/InstructTuning/mmlu/quant/quantizer.py:37
↓ 2 callersMethod_remove_eos
(gen)
Experiments/LanguageGeneration/HumanEval/model.py:279
↓ 2 callersFunctionadd_variable_to_config
(cfg: CfgNode, name: str, value)
Experiments/InstructTuning/bbh/src/main.py:30
↓ 2 callersFunctionannotate
(prompt, logit_bias=None)
Experiments/HumanAlignment/model/davinci-002.py:74
↓ 2 callersFunctionannotate
( prompt, model="claude-instant-v1", stop=None, max_tokens=512, )
Experiments/HumanAlignment/model/Claude.py:23
↓ 2 callersFunctionannotate
(prompt, logit_bias=None)
Experiments/HumanAlignment/model/davinci-003.py:74
↓ 2 callersFunctionannotate
(prompt, logit_bias=None)
Experiments/HumanAlignment/metric/eval_truthfulqa.py:76
↓ 2 callersFunctionast_parse
(candidate, lang='python')
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/ast_eval_hf.py:42
↓ 2 callersFunctionast_parse
(candidate, lang='python')
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/ast_eval_tf.py:42
↓ 2 callersFunctioncalculate_sentence_perplexity
(model, tokenizer, sentence)
Experiments/HumanAlignment/metric/crows_pairs.py:16
↓ 2 callersFunctionclean_str
(p)
Experiments/ToolManipulation/HotPotQA/wikienv.py:12
↓ 2 callersFunctioncorpus_syntax_match
Language.build_library(# Store the library in the `build` directory 'build/my-languages.so', 'vendor/tree-sitter-python')
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/syntax_match.py:24
↓ 2 callersFunctiondel_answer_text
(content)
Experiments/MathematicalReasoning/evaluate_falcon.py:42
↓ 2 callersFunctiondel_answer_text
(content)
Experiments/MathematicalReasoning/evaluate.py:42
↓ 2 callersFunctiondump_jsonl
Write list of objects to a JSON lines file.
Experiments/HumanAlignment/HaluEval/openai_gpt.py:113
↓ 2 callersFunctionencode_question
Encode multiple prompt instructions into a single string.
Experiments/ToolManipulation/Gorilla/eval/utils.py:6
↓ 2 callersFunctionformat_example
(df, idx, include_answer=True)
Experiments/InstructTuning/mmlu/mmlu.py:116
↓ 2 callersFunctionformat_ft_comp
Formats prompt for fine-tuned semantic similarity with GPT-3
Experiments/HumanAlignment/metric/eval_truthfulqa.py:101
↓ 2 callersFunctiongen_prompt
(train_df, subject, k=-1)
Experiments/InstructTuning/mmlu/mmlu.py:127
↓ 2 callersFunctionget_all_sub_trees
(root_node)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/syntax_check.py:49
↓ 2 callersFunctionget_all_sub_trees
(root_node)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/syntax_match.py:69
↓ 2 callersFunctionget_answer_boxed
(content)
Experiments/MathematicalReasoning/test_falcon_math.py:33
↓ 2 callersFunctionget_data_flow
(code, parser)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/dataflow_match.py:59
↓ 2 callersFunctionget_exist_dialog_set
()
Experiments/HumanAlignment/model/davinci-002.py:26
↓ 2 callersFunctionget_exist_dialog_set
()
Experiments/HumanAlignment/model/Claude.py:16
↓ 2 callersFunctionget_exist_dialog_set
()
Experiments/HumanAlignment/model/ChatGPT.py:26
↓ 2 callersFunctionget_exist_dialog_set
()
Experiments/HumanAlignment/model/Pythia.py:21
↓ 2 callersFunctionget_exist_dialog_set
()
Experiments/HumanAlignment/model/Alpaca.py:21
↓ 2 callersFunctionget_exist_dialog_set
()
Experiments/HumanAlignment/model/davinci-003.py:26
↓ 2 callersFunctionget_exist_dialog_set
()
Experiments/HumanAlignment/metric/real-toxicity-prompts.py:15
↓ 2 callersFunctionget_exist_dialog_set
()
Experiments/HumanAlignment/metric/eval_truthfulqa.py:28
↓ 2 callersFunctionget_history
()
Experiments/KnowledgeUtilization/WikiFact/wikifact_claude.py:13
↓ 2 callersFunctionget_history
()
Experiments/LanguageGeneration/WMT22/wmt_claude.py:13
↓ 2 callersFunctionget_history
()
Experiments/LanguageGeneration/LAMBADA/lambada_claude.py:13
↓ 2 callersFunctionget_history
()
Experiments/LanguageGeneration/XSum/xsum_claude.py:13
↓ 2 callersFunctionget_history
()
Experiments/HumanAlignment/HaluEval/claude_halu.py:13
↓ 2 callersMethodget_history
(self)
Experiments/LanguageGeneration/HumanEval/model.py:116
↓ 2 callersFunctionget_subcategories
()
Experiments/InstructTuning/mmlu/mmlu.py:24
↓ 2 callersFunctionllm
(prompt, stop=["\n"])
Experiments/ToolManipulation/HotPotQA/hotpotqa-claude.py:19
↓ 2 callersFunctionllm
(prompt, stop=["\n"])
Experiments/ToolManipulation/HotPotQA/hotpotqa-chat.py:31
↓ 2 callersFunctionllm
(prompt, stop=["\n"])
Experiments/ToolManipulation/HotPotQA/hotpotqa.py:29
↓ 2 callersFunctionllm
(prompt, stop=["\n"])
Experiments/ToolManipulation/HotPotQA/hotpotqa-hf.py:60
↓ 2 callersMethodload
(self)
Experiments/InstructTuning/mmlu/modeling.py:51
↓ 2 callersMethodload
(self)
Experiments/InstructTuning/mmlu/modeling.py:95
↓ 2 callersFunctionload_cfg
(cfg_file: str, new_allowed: bool=True)
Experiments/InstructTuning/bbh/src/main.py:36
↓ 2 callersFunctionload_quant
( model, checkpoint, wbits, groupsize=-1, fused_mlp=True, warmup_autotune=True, )
Experiments/InstructTuning/mmlu/modeling.py:230
↓ 2 callersFunctionmake_query
(batch)
Experiments/SymbolicReasoning/solve_text_003.py:133
↓ 2 callersFunctionmake_query
()
Experiments/SymbolicReasoning/test_falcon_penguins.py:83
↓ 2 callersFunctionmake_query
()
Experiments/SymbolicReasoning/test_falcon_color.py:87
↓ 2 callersFunctionmake_query
(batch)
Experiments/SymbolicReasoning/solve_text_002.py:133
↓ 2 callersFunctionmake_query
(batch)
Experiments/MathematicalReasoning/solve_text_003.py:133
↓ 2 callersFunctionmake_query
()
Experiments/MathematicalReasoning/test_falcon_math.py:102
↓ 2 callersFunctionmake_query
()
Experiments/MathematicalReasoning/test_falcon_gsm8k.py:85
↓ 2 callersFunctionmake_query
(batch)
Experiments/MathematicalReasoning/solve_text_002.py:133
↓ 2 callersFunctionmatmul248
(input, qweight, scales, qzeros, g_idx, bits, maxq)
Experiments/InstructTuning/mmlu/quant/quant_linear.py:394
↓ 2 callersFunctionmove_reduce_sign
(text)
Experiments/MathematicalReasoning/evaluate_falcon.py:173
↓ 2 callersFunctionmove_reduce_sign
(text)
Experiments/MathematicalReasoning/evaluate.py:172
↓ 2 callersFunctionnormalize_dataflow
(dataflow)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/dataflow_match.py:120
↓ 2 callersFunctionnum_tokens_from_message
(message, model="text-davinci-002")
Experiments/LanguageGeneration/XSum/xsum_002.py:8
↓ 2 callersFunctionnum_tokens_from_message
(message, model="text-davinci-003")
Experiments/LanguageGeneration/XSum/xsum_003.py:8
↓ 2 callersFunctionnum_tokens_from_message
(message, model="gpt-3.5-turbo")
Experiments/LanguageGeneration/XSum/xsum_chatgpt.py:8
↓ 2 callersMethodprocess_single_data
(self, data)
Experiments/SymbolicReasoning/data_process.py:305
next →1–100 of 1,088, ranked by callers