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
↓ 2 callersMethodprocess_single_data
(self, data)
Experiments/MathematicalReasoning/data_process.py:305
↓ 2 callersMethodprune_configs
(self, kwargs)
Experiments/InstructTuning/mmlu/quant/custom_autotune.py:133
↓ 2 callersMethodrun
(self, prompt: str, **kwargs)
Experiments/InstructTuning/mmlu/modeling.py:33
↓ 2 callersFunctionselect_model
(model_name: str, **kwargs)
Experiments/InstructTuning/mmlu/modeling.py:338
↓ 2 callersFunctionsmart_tokenizer_and_embedding_resize
Resize tokenizer and embedding. Note: This is the unoptimized version that may make your embedding size not be divisible by 64.
Experiments/HumanAlignment/model/train.py:67
↓ 2 callersFunctionsplit_files
(model_path, tmp_path, split_size)
Experiments/ToolManipulation/Gorilla/inference/apply_delta.py:27
↓ 2 callersFunctionstep
(env, action)
Experiments/ToolManipulation/HotPotQA/hotpotqa-claude.py:55
↓ 2 callersFunctionstep
(env, action)
Experiments/ToolManipulation/HotPotQA/hotpotqa-chat.py:80
↓ 2 callersFunctionstep
(env, action)
Experiments/ToolManipulation/HotPotQA/hotpotqa.py:76
↓ 2 callersFunctionstep
(env, action)
Experiments/ToolManipulation/HotPotQA/hotpotqa-hf.py:85
↓ 2 callersFunctiontranspose_matmul248
(input, qweight, scales, qzeros, g_idx, bits, maxq)
Experiments/InstructTuning/mmlu/quant/quant_linear.py:427
↓ 2 callersMethodtriton_llama_mlp
(self, x)
Experiments/InstructTuning/mmlu/quant/fused_mlp.py:287
↓ 2 callersFunctionweighted_sum
(weights, counts)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/weighted_ngram_match.py:244
↓ 2 callersFunctionwrite_result_to_file
(result, output_file)
Experiments/ToolManipulation/Gorilla/eval/get_llm_responses.py:94
↓ 1 callersMethod__clean
(self, content)
Experiments/SymbolicReasoning/data_process.py:265
↓ 1 callersMethod__clean
(self, content)
Experiments/MathematicalReasoning/data_process.py:265
↓ 1 callersMethod_bench
(self, *args, config, **meta)
Experiments/InstructTuning/mmlu/quant/custom_autotune.py:64
↓ 1 callersMethod_chatgpt_parse
(self, ret, prompt)
Experiments/LanguageGeneration/HumanEval/model.py:286
↓ 1 callersMethod_get_info
(self)
Experiments/ToolManipulation/HotPotQA/wrappers.py:101
↓ 1 callersMethod_get_info
(self)
Experiments/ToolManipulation/HotPotQA/wrappers.py:170
↓ 1 callersMethod_get_obs
(self)
Experiments/ToolManipulation/HotPotQA/wikienv.py:41
↓ 1 callersFunction_tokenize_fn
Tokenize a list of strings.
Experiments/InstructTuning/train.py:94
↓ 1 callersFunctionanalyze_text
(text)
Experiments/HumanAlignment/metric/real-toxicity-prompts.py:22
↓ 1 callersFunctionannotate
(message)
Experiments/KnowledgeUtilization/WikiFact/wikifact_claude.py:19
↓ 1 callersFunctionannotate
(message)
Experiments/LanguageGeneration/WMT22/wmt_claude.py:19
↓ 1 callersFunctionannotate
(message)
Experiments/LanguageGeneration/LAMBADA/lambada_claude.py:19
↓ 1 callersFunctionannotate
(message)
Experiments/LanguageGeneration/XSum/xsum_claude.py:19
↓ 1 callersFunctionannotate
(message)
Experiments/HumanAlignment/HaluEval/claude_halu.py:19
↓ 1 callersFunctionannotate
(prompt, logit_bias=None)
Experiments/KnowledgeReasoning/davinci-002.py:75
↓ 1 callersFunctionannotate
(prompt)
Experiments/KnowledgeReasoning/Claude.py:30
↓ 1 callersFunctionannotate
(prompt, logit_bias=None)
Experiments/KnowledgeReasoning/ChatGPT.py:73
↓ 1 callersFunctionannotate
(prompt, logit_bias=None)
Experiments/KnowledgeReasoning/davinci-003.py:75
↓ 1 callersFunctionapply_delta
(base_model_path, target_model_path, delta_path)
Experiments/ToolManipulation/Gorilla/inference/apply_delta.py:127
↓ 1 callersFunctionapply_delta_low_cpu_mem
(base_model_path, target_model_path, delta_path)
Experiments/ToolManipulation/Gorilla/inference/apply_delta.py:72
↓ 1 callersFunctionast_check
(candidate_subtree_list, base_tree_list)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/ast_eval_th.py:75
↓ 1 callersFunctionast_check
(candidate_subtree_list, base_tree_list)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/ast_eval_hf.py:65
↓ 1 callersFunctionast_check
(candidate_subtree_list, base_tree_list)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/ast_eval_tf.py:65
↓ 1 callersFunctionast_parse
(candidate, lang="python")
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/ast_eval_th.py:54
↓ 1 callersFunctionbrevity_penalty
Calculate brevity penalty. As the modified n-gram precision still has the problem from the short length sentence, brevity penalty is u
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/bleu.py:322
↓ 1 callersFunctionbrevity_penalty
Calculate brevity penalty. As the modified n-gram precision still has the problem from the short length sentence, brevity penalty is u
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/weighted_ngram_match.py:290
↓ 1 callersFunctioncal_crows_res
(dataset)
Experiments/HumanAlignment/metric/cal_crows_res.py:8
↓ 1 callersFunctioncal_crows_res_api
(dataset)
Experiments/HumanAlignment/metric/cal_crows_res.py:24
↓ 1 callersFunctioncal_res
(dataset)
Experiments/HumanAlignment/metric/Winogender.py:8
↓ 1 callersFunctioncal_res_api
(dataset)
Experiments/HumanAlignment/metric/Winogender.py:49
↓ 1 callersFunctioncal_toxicity_score
(dataset)
Experiments/HumanAlignment/metric/cal_toxicity_score.py:9
↓ 1 callersMethodcalc_acc
(self, prompts: List[Dict], preds: List[str])
Experiments/InstructTuning/bbh/src/BBH10KBenchmark.py:40
↓ 1 callersFunctioncalc_res
(dataset_path)
Experiments/HumanAlignment/metric/cal_truth_res.py:10
↓ 1 callersFunctioncalculate_co_reference_accuracy
(sentence)
Experiments/HumanAlignment/metric/cal_wino_res.py:14
↓ 1 callersFunctioncall_chat_completion
(prompt, stop_word='Problem')
Experiments/SymbolicReasoning/solve_turbo.py:37
↓ 1 callersFunctioncall_chat_completion
(prompt, stop_word='Problem')
Experiments/MathematicalReasoning/solve_turbo.py:37
↓ 1 callersFunctioncall_claude_completion
( prompt, model="claude-instant-v1", stop=None, max_tokens=512, )
Experiments/SymbolicReasoning/claude.py:14
↓ 1 callersFunctioncall_claude_completion
( prompt, model="claude-instant-v1", stop=None, max_tokens=512, )
Experiments/SymbolicReasoning/solve_claude.py:39
↓ 1 callersFunctioncall_claude_completion
( prompt, model="claude-instant-v1", stop=None, max_tokens=512, )
Experiments/MathematicalReasoning/claude.py:14
↓ 1 callersFunctioncall_claude_completion
( prompt, model="claude-instant-v1", stop=None, max_tokens=512, )
Experiments/MathematicalReasoning/solve_claude.py:39
↓ 1 callersFunctioncall_completion
(prompt, stop_word='Problem')
Experiments/SymbolicReasoning/solve_text_003.py:32
↓ 1 callersFunctioncall_completion
(prompt, stop_word='Problem')
Experiments/SymbolicReasoning/solve_text_002.py:32
↓ 1 callersFunctioncall_completion
(prompt, stop_word='Problem')
Experiments/MathematicalReasoning/solve_text_003.py:32
↓ 1 callersFunctioncall_completion
(prompt, stop_word='Problem')
Experiments/MathematicalReasoning/solve_text_002.py:32
↓ 1 callersFunctionchange_api
()
Experiments/ToolManipulation/HotPotQA/hotpotqa-chat.py:20
↓ 1 callersFunctionchange_api
()
Experiments/ToolManipulation/HotPotQA/hotpotqa.py:18
↓ 1 callersFunctionchange_api
()
Experiments/ToolManipulation/Gorilla/eval/utils.py:34
↓ 1 callersMethodcheck_valid_length
(self, text: str)
Experiments/InstructTuning/mmlu/modeling.py:39
↓ 1 callersFunctionclean
(content)
Experiments/MathematicalReasoning/do_gsm8k.py:341
↓ 1 callersFunctionclean
(content)
Experiments/MathematicalReasoning/test_falcon_gsm8k.py:12
↓ 1 callersFunctionclosest_ref_length
This function finds the reference that is the closest length to the hypothesis. The closest reference length is referred to as *r* variable
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/bleu.py:303
↓ 1 callersFunctionclosest_ref_length
This function finds the reference that is the closest length to the hypothesis. The closest reference length is referred to as *r* variable
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/weighted_ngram_match.py:271
↓ 1 callersFunctioncode_generate
(args, workdir: PathLike, model: DecoderBase)
Experiments/LanguageGeneration/HumanEval/generate.py:41
↓ 1 callersMethodcodegen
( self, prompt: str, do_sample: bool = True, num_samples: int = 200 )
Experiments/LanguageGeneration/HumanEval/model.py:92
↓ 1 callersMethodconstruct_lookup_list
(self, keyword)
Experiments/ToolManipulation/HotPotQA/wikienv.py:62
↓ 1 callersFunctioncorpus_bleu
Calculate a single corpus-level BLEU score (aka. system-level BLEU) for all the hypotheses and their respective references. Instead of
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/bleu.py:91
↓ 1 callersFunctioncorpus_bleu
Calculate a single corpus-level BLEU score (aka. system-level BLEU) for all the hypotheses and their respective references. Instead of
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/weighted_ngram_match.py:94
↓ 1 callersFunctioncorpus_dataflow_match
(references, candidates, lang)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/dataflow_match.py:19
↓ 1 callersMethodcount_text_length
(self, text: str)
Experiments/InstructTuning/mmlu/modeling.py:36
↓ 1 callersFunctioncreate_chatgpt_config
( message: str, max_tokens: int, temperature: float = 1, batch_size: int = 1, system_messa
Experiments/LanguageGeneration/HumanEval/util.py:9
↓ 1 callersFunctioncreate_davinci_config
( # message: str, prompt: str, max_tokens: int, temperature: float = 1, batch_size: int =
Experiments/LanguageGeneration/HumanEval/util.py:29
↓ 1 callersFunctiondump_jsonl
Write list of objects to a JSON lines file.
Experiments/KnowledgeUtilization/WikiFact/wikifact_claude.py:36
↓ 1 callersFunctiondump_jsonl
Write list of objects to a JSON lines file.
Experiments/KnowledgeUtilization/WikiFact/open-source_model.py:82
↓ 1 callersFunctiondump_jsonl
Write list of objects to a JSON lines file.
Experiments/KnowledgeUtilization/WikiFact/wikifact_002.py:53
↓ 1 callersFunctiondump_jsonl
Write list of objects to a JSON lines file.
Experiments/KnowledgeUtilization/WikiFact/wikifact_003.py:53
↓ 1 callersFunctiondump_jsonl
Write list of objects to a JSON lines file.
Experiments/KnowledgeUtilization/WikiFact/wikifact_chatgpt.py:56
↓ 1 callersFunctiondump_jsonl
Write list of objects to a JSON lines file.
Experiments/LanguageGeneration/WMT22/wmt-002.py:55
↓ 1 callersFunctiondump_jsonl
Write list of objects to a JSON lines file.
Experiments/LanguageGeneration/WMT22/wmt-003.py:55
↓ 1 callersFunctiondump_jsonl
Write list of objects to a JSON lines file.
Experiments/LanguageGeneration/WMT22/open-source_model.py:86
↓ 1 callersFunctiondump_jsonl
Write list of objects to a JSON lines file.
Experiments/LanguageGeneration/WMT22/wmt_chatgpt.py:57
↓ 1 callersFunctiondump_jsonl
Write list of objects to a JSON lines file.
Experiments/LanguageGeneration/WMT22/wmt_claude.py:36
↓ 1 callersFunctiondump_jsonl
Write list of objects to a JSON lines file.
Experiments/LanguageGeneration/LAMBADA/lambada_002.py:62
↓ 1 callersFunctiondump_jsonl
Write list of objects to a JSON lines file.
Experiments/LanguageGeneration/LAMBADA/lambada_003.py:61
↓ 1 callersFunctiondump_jsonl
Write list of objects to a JSON lines file.
Experiments/LanguageGeneration/LAMBADA/lambada_claude.py:35
↓ 1 callersFunctiondump_jsonl
Write list of objects to a JSON lines file.
Experiments/LanguageGeneration/LAMBADA/lambada_chatgpt.py:63
↓ 1 callersFunctiondump_jsonl
Write list of objects to a JSON lines file.
Experiments/LanguageGeneration/XSum/open-source_model.py:87
↓ 1 callersFunctiondump_jsonl
Write list of objects to a JSON lines file.
Experiments/LanguageGeneration/XSum/xsum_002.py:66
↓ 1 callersFunctiondump_jsonl
Write list of objects to a JSON lines file.
Experiments/LanguageGeneration/XSum/xsum_003.py:66
↓ 1 callersFunctiondump_jsonl
Write list of objects to a JSON lines file.
Experiments/LanguageGeneration/XSum/xsum_claude.py:36
↓ 1 callersFunctiondump_jsonl
Write list of objects to a JSON lines file.
Experiments/LanguageGeneration/XSum/xsum_chatgpt.py:69
↓ 1 callersFunctiondump_jsonl
Write list of objects to a JSON lines file.
Experiments/HumanAlignment/HaluEval/claude_halu.py:37
↓ 1 callersFunctiondump_jsonl
Write list of objects to a JSON lines file.
Experiments/HumanAlignment/HaluEval/open-source_model.py:97
↓ 1 callersFunctionevaluate
( instruction, input=None, temperature=0.1, top_p=0.75, top_k=40,
Experiments/InstructTuning/auto_eval/generate.py:47
↓ 1 callersFunctionevaluate
(args, subject, model: EvalModel, dev_df, test_df)
Experiments/InstructTuning/mmlu/mmlu.py:138
↓ 1 callersMethodevaluate_model
(self, model: Model)
Experiments/InstructTuning/bbh/src/BBH10KBenchmark.py:61
↓ 1 callersFunctionevaluation_dataset
(model, file, output_path)
Experiments/HumanAlignment/HaluEval/openai_gpt.py:70
← previousnext →101–200 of 1,088, ranked by callers