Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/RUCAIBox/LLMSurvey
/ functions
Functions
1,088 in github.com/RUCAIBox/LLMSurvey
⨍
Functions
1,088
◇
Types & classes
151
↳
Endpoints
1
↓ 1 callers
Function
main
()
Experiments/SymbolicReasoning/do_color.py:374
↓ 1 callers
Function
main
(args)
Experiments/SymbolicReasoning/solve_claude.py:89
↓ 1 callers
Function
main
(args)
Experiments/SymbolicReasoning/solve_text_002.py:72
↓ 1 callers
Function
main
(args)
Experiments/SymbolicReasoning/evaluate_penguins.py:33
↓ 1 callers
Function
main
()
Experiments/SymbolicReasoning/do_penguins.py:366
↓ 1 callers
Function
main
(args)
Experiments/SymbolicReasoning/solve_turbo.py:100
↓ 1 callers
Function
main
(args)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/ast_eval_th.py:173
↓ 1 callers
Function
main
(args)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/ast_eval_hf.py:117
↓ 1 callers
Function
main
(args)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/ast_eval_tf.py:117
↓ 1 callers
Function
main
(args)
Experiments/MathematicalReasoning/evaluate_falcon.py:255
↓ 1 callers
Function
main
(args)
Experiments/MathematicalReasoning/solve_text_003.py:72
↓ 1 callers
Function
main
()
Experiments/MathematicalReasoning/do_gsm8k.py:350
↓ 1 callers
Function
main
(args)
Experiments/MathematicalReasoning/solve_claude.py:89
↓ 1 callers
Function
main
(args)
Experiments/MathematicalReasoning/solve_text_002.py:72
↓ 1 callers
Function
main
()
Experiments/MathematicalReasoning/do_math.py:365
↓ 1 callers
Function
main
(args)
Experiments/MathematicalReasoning/evaluate.py:244
↓ 1 callers
Function
main
(args)
Experiments/MathematicalReasoning/solve_turbo.py:100
↓ 1 callers
Function
make_model
(name: str, batch_size: int = 1, temperature: float = 0.8, path: str = None)
Experiments/LanguageGeneration/HumanEval/model.py:348
↓ 1 callers
Function
make_supervised_data_module
Make dataset and collator for supervised fine-tuning.
Experiments/InstructTuning/train.py:223
↓ 1 callers
Method
method4
Smoothing method 4: Shorter translations may have inflated precision values due to having smaller denominators; therefore,
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/bleu.py:521
↓ 1 callers
Method
method4
Smoothing method 4: Shorter translations may have inflated precision values due to having smaller denominators; therefore,
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/weighted_ngram_match.py:489
↓ 1 callers
Method
method5
Smoothing method 5: The matched counts for similar values of n should be similar. To a calculate the n-gram matched count,
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/bleu.py:538
↓ 1 callers
Method
method5
Smoothing method 5: The matched counts for similar values of n should be similar. To a calculate the n-gram matched count,
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/weighted_ngram_match.py:506
↓ 1 callers
Function
modified_recall
Calculate modified ngram recall. :param references: A list of reference translations. :type references: list(list(str)) :param hy
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/weighted_ngram_match.py:209
↓ 1 callers
Function
pad_sequence
Returns a padded sequence of items before ngram extraction. >>> list(pad_sequence([1,2,3,4,5], 2, pad_left=True, pad_right=True, left_p
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/utils.py:10
↓ 1 callers
Function
parse_args
()
Experiments/InstructTuning/bbh/src/main.py:42
↓ 1 callers
Function
parse_dataset
(args)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/ast_eval_th.py:99
↓ 1 callers
Function
parse_dataset
(args)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/ast_eval_hf.py:89
↓ 1 callers
Function
parse_dataset
(args)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/ast_eval_tf.py:89
↓ 1 callers
Function
preprocess
Preprocess the data by tokenizing.
Experiments/InstructTuning/train.py:134
↓ 1 callers
Method
ready
(self)
Experiments/InstructTuning/mmlu/quant/quantizer.py:137
↓ 1 callers
Function
remove_articles
(text: str)
Experiments/KnowledgeUtilization/WikiFact/em.py:12
↓ 1 callers
Function
remove_articles
(text)
Experiments/ToolManipulation/HotPotQA/wrappers.py:43
↓ 1 callers
Function
remove_punc
(text: str)
Experiments/KnowledgeUtilization/WikiFact/em.py:18
↓ 1 callers
Function
remove_punc
(text)
Experiments/ToolManipulation/HotPotQA/wrappers.py:49
↓ 1 callers
Function
request_chatgpt_engine
(config)
Experiments/LanguageGeneration/HumanEval/util.py:57
↓ 1 callers
Function
request_gpt3_engine
(config)
Experiments/LanguageGeneration/HumanEval/util.py:80
↓ 1 callers
Method
run
(self, *args, **kwargs)
Experiments/InstructTuning/mmlu/quant/custom_autotune.py:96
↓ 1 callers
Function
run_eval
(args, test_data)
Experiments/KnowledgeUtilization/WikiFact/open-source_model.py:56
↓ 1 callers
Function
run_eval
(args, test_data)
Experiments/LanguageGeneration/WMT22/open-source_model.py:59
↓ 1 callers
Function
run_eval
(args, test_data)
Experiments/LanguageGeneration/XSum/open-source_model.py:57
↓ 1 callers
Function
run_eval
()
Experiments/HumanAlignment/model/ChatGLM.py:50
↓ 1 callers
Function
run_eval
(args, test_data)
Experiments/HumanAlignment/HaluEval/open-source_model.py:56
↓ 1 callers
Function
run_eval
(args, data_id2data, data_id_set, mode)
Experiments/KnowledgeReasoning/get_response.py:89
↓ 1 callers
Function
run_eval
(args, question_jsons)
Experiments/ToolManipulation/Gorilla/eval/get_hf_responses.py:61
↓ 1 callers
Function
run_eval
(args, question_jsons)
Experiments/ToolManipulation/Gorilla/inference/gorilla_eval.py:88
↓ 1 callers
Function
save_benchmark
(model, language, cache_path, responses)
Experiments/InstructTuning/bbh/src/BBH10KBenchmark.py:12
↓ 1 callers
Method
search_step
(self, entity)
Experiments/ToolManipulation/HotPotQA/wikienv.py:101
↓ 1 callers
Function
set_logger
(log_file, name="default")
Experiments/InstructTuning/bbh/src/main.py:15
↓ 1 callers
Function
silu
(x)
Experiments/InstructTuning/mmlu/quant/fused_mlp.py:252
↓ 1 callers
Function
smart_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/InstructTuning/train.py:71
↓ 1 callers
Function
test_main
()
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/examples/python3-grammar.py:941
↓ 1 callers
Function
test_main
()
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/examples/python3-grammar-crlf.py:941
↓ 1 callers
Function
test_main
()
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/examples/python2-grammar.py:970
↓ 1 callers
Function
test_main
()
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/examples/python2-grammar-crlf.py:969
↓ 1 callers
Method
test_max_length
(self)
Experiments/InstructTuning/mmlu/modeling.py:308
↓ 1 callers
Function
train
()
Experiments/InstructTuning/train.py:230
↓ 1 callers
Function
tree_to_token_index
(root_node)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/utils.py:67
↓ 1 callers
Function
triton_rotate_half_
(qk, position_ids, config=None)
Experiments/InstructTuning/mmlu/quant/fused_attn.py:64
↓ 1 callers
Function
truncate_message
(prompt, model="davinci")
Experiments/HumanAlignment/HaluEval/openai_gpt.py:17
↓ 1 callers
Method
update_record
(self)
Experiments/ToolManipulation/HotPotQA/wrappers.py:228
↓ 1 callers
Function
webthink
(idx=None, prompt=webthink_prompt, to_print=True)
Experiments/ToolManipulation/HotPotQA/hotpotqa-claude.py:97
↓ 1 callers
Function
webthink
(idx=None, prompt_messages=prompt_messages, to_print=True)
Experiments/ToolManipulation/HotPotQA/hotpotqa-chat.py:126
↓ 1 callers
Function
webthink
(idx=None, prompt=webthink_prompt, to_print=True)
Experiments/ToolManipulation/HotPotQA/hotpotqa.py:104
↓ 1 callers
Function
webthink
(idx=None, prompt=webthink_prompt, to_print=True)
Experiments/ToolManipulation/HotPotQA/hotpotqa-hf.py:113
↓ 1 callers
Function
white_space_fix
(text: str)
Experiments/KnowledgeUtilization/WikiFact/em.py:15
↓ 1 callers
Function
white_space_fix
(text)
Experiments/ToolManipulation/HotPotQA/wrappers.py:46
Function
DFG_csharp
(root_node,index_to_code,states)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/DFG.py:358
Function
DFG_go
(root_node,index_to_code,states)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/DFG.py:697
Function
DFG_java
(root_node,index_to_code,states)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/DFG.py:182
Function
DFG_javascript
(root_node,index_to_code,states)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/DFG.py:1024
Function
DFG_php
(root_node,index_to_code,states)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/DFG.py:839
Function
DFG_python
(root_node,index_to_code,states)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/DFG.py:11
Function
DFG_ruby
(root_node,index_to_code,states)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/DFG.py:538
Method
__aenter__
(self)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/examples/python3.8_grammar.py:1547
Method
__aexit__
(self, *exc)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/examples/python3.8_grammar.py:1549
Method
__aiter__
(self)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/examples/python3.8_grammar.py:1524
Method
__anext__
(self)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/examples/python3.8_grammar.py:1526
Method
__call__
(self, instances: Sequence[Dict])
Experiments/InstructTuning/train.py:210
Method
__call__
Returns true if all generated sequences contain any of the end-of-function strings.
Experiments/LanguageGeneration/HumanEval/model.py:44
Method
__call__
(self, retry_state: "RetryCallState")
Experiments/HumanAlignment/model/davinci-002.py:51
Method
__call__
(self, retry_state: "RetryCallState")
Experiments/HumanAlignment/model/davinci-002.py:69
Method
__call__
(self, retry_state: "RetryCallState")
Experiments/HumanAlignment/model/ChatGPT.py:51
Method
__call__
(self, retry_state: "RetryCallState")
Experiments/HumanAlignment/model/ChatGPT.py:69
Method
__call__
(self, retry_state: "RetryCallState")
Experiments/HumanAlignment/model/davinci-003.py:51
Method
__call__
(self, retry_state: "RetryCallState")
Experiments/HumanAlignment/model/davinci-003.py:69
Method
__call__
(self, retry_state: "RetryCallState")
Experiments/HumanAlignment/metric/eval_truthfulqa.py:53
Method
__call__
(self, retry_state: "RetryCallState")
Experiments/HumanAlignment/metric/eval_truthfulqa.py:71
Method
__call__
(self, retry_state: "RetryCallState")
Experiments/KnowledgeReasoning/davinci-002.py:52
Method
__call__
(self, retry_state: "RetryCallState")
Experiments/KnowledgeReasoning/davinci-002.py:70
Method
__call__
(self, retry_state: "RetryCallState")
Experiments/KnowledgeReasoning/ChatGPT.py:50
Method
__call__
(self, retry_state: "RetryCallState")
Experiments/KnowledgeReasoning/ChatGPT.py:68
Method
__call__
(self, retry_state: "RetryCallState")
Experiments/KnowledgeReasoning/davinci-003.py:52
Method
__call__
(self, retry_state: "RetryCallState")
Experiments/KnowledgeReasoning/davinci-003.py:70
Method
__call__
(self, examples)
Experiments/SymbolicReasoning/do_color.py:292
Method
__call__
(self, examples)
Experiments/SymbolicReasoning/do_penguins.py:290
Method
__call__
(self, examples)
Experiments/MathematicalReasoning/do_gsm8k.py:291
Method
__call__
(self, examples)
Experiments/MathematicalReasoning/do_math.py:289
Method
__enter__
(self)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/examples/python3-grammar.py:855
Method
__enter__
(self)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/examples/python3-grammar-crlf.py:855
← previous
next →
301–400 of 1,088, ranked by callers