MCPcopy Create free account

hub / github.com/RUCAIBox/LLMSurvey / functions

Functions1,088 in github.com/RUCAIBox/LLMSurvey

Functionmake_quant_attn
Replace all LlamaAttention modules with QuantLlamaAttention modules, fusing the q, k, v projections.
Experiments/InstructTuning/mmlu/quant/fused_attn.py:192
Functionmake_quant_linear
(module, names, bits, groupsize, name="")
Experiments/InstructTuning/mmlu/quant/quant_linear.py:598
Functionmake_quant_norm
Replace all LlamaRMSNorm modules with TritonLlamaRMSNorm modules
Experiments/InstructTuning/mmlu/quant/triton_norm.py:78
Functionmatmul248_kernel_config_pruner
The main purpose of this function is to shrink BLOCK_SIZE_* when the corresponding dimension is smaller.
Experiments/InstructTuning/mmlu/quant/custom_autotune.py:217
Functionmatmul_248_kernel
Compute the matrix multiplication C = A x B. A is of shape (M, K) float16 B is of shape (K//8, N) int32 C is of shape
Experiments/InstructTuning/mmlu/quant/quant_linear.py:105
Methodmeth1
(self)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/examples/python3-grammar.py:718
Methodmeth1
(self)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/examples/python3-grammar-crlf.py:718
Methodmeth1
(self)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/examples/python2-grammar.py:751
Methodmeth1
(self)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/examples/python3.8_grammar.py:1295
Methodmeth1
(self)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/examples/python2-grammar-crlf.py:750
Methodmeth2
(self, arg)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/examples/python3-grammar.py:719
Methodmeth2
(self, arg)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/examples/python3-grammar-crlf.py:719
Methodmeth2
(self, arg)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/examples/python2-grammar.py:752
Methodmeth2
(self, arg)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/examples/python3.8_grammar.py:1296
Methodmeth2
(self, arg)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/examples/python2-grammar-crlf.py:751
Methodmeth3
(self, a1, a2)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/examples/python3-grammar.py:720
Methodmeth3
(self, a1, a2)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/examples/python3-grammar-crlf.py:720
Methodmeth3
(self, a1, a2)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/examples/python2-grammar.py:753
Methodmeth3
(self, a1, a2)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/examples/python3.8_grammar.py:1297
Methodmeth3
(self, a1, a2)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/examples/python2-grammar-crlf.py:752
Methodmethod0
No smoothing.
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/bleu.py:451
Methodmethod0
No smoothing.
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/weighted_ngram_match.py:419
Methodmethod1
Smoothing method 1: Add *epsilon* counts to precision with 0 counts.
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/bleu.py:476
Methodmethod1
Smoothing method 1: Add *epsilon* counts to precision with 0 counts.
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/weighted_ngram_match.py:444
Methodmethod2
Smoothing method 2: Add 1 to both numerator and denominator from Chin-Yew Lin and Franz Josef Och (2004) Automatic evaluation of
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/bleu.py:487
Methodmethod2
Smoothing method 2: Add 1 to both numerator and denominator from Chin-Yew Lin and Franz Josef Och (2004) Automatic evaluation of
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/weighted_ngram_match.py:455
Methodmethod3
Smoothing method 3: NIST geometric sequence smoothing The smoothing is computed by taking 1 / ( 2^k ), instead of 0, for each
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/bleu.py:499
Methodmethod3
Smoothing method 3: NIST geometric sequence smoothing The smoothing is computed by taking 1 / ( 2^k ), instead of 0, for each
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/weighted_ngram_match.py:467
Methodmethod6
Smoothing method 6: Interpolates the maximum likelihood estimate of the precision *p_n* with a prior estimate *pi0*. The p
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/bleu.py:555
Methodmethod6
Smoothing method 6: Interpolates the maximum likelihood estimate of the precision *p_n* with a prior estimate *pi0*. The p
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/weighted_ngram_match.py:523
Methodmethod7
Smoothing method 7: Interpolates methods 4 and 5.
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/bleu.py:582
Methodmethod7
Smoothing method 7: Interpolates methods 4 and 5.
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/weighted_ngram_match.py:550
Functionmy_before_sleep
(retry_state)
Experiments/HumanAlignment/model/davinci-002.py:33
Functionmy_before_sleep
(retry_state)
Experiments/HumanAlignment/model/ChatGPT.py:33
Functionmy_before_sleep
(retry_state)
Experiments/HumanAlignment/model/davinci-003.py:33
Functionmy_before_sleep
(retry_state)
Experiments/HumanAlignment/metric/eval_truthfulqa.py:35
Functionmy_before_sleep
(retry_state)
Experiments/KnowledgeReasoning/davinci-002.py:34
Functionmy_before_sleep
(retry_state)
Experiments/KnowledgeReasoning/ChatGPT.py:32
Functionmy_before_sleep
(retry_state)
Experiments/KnowledgeReasoning/davinci-003.py:34
Functionnoop
(*args, **kwargs)
Experiments/InstructTuning/mmlu/modeling.py:225
Functionnormalize_dataflow_item
(dataflow_item)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/dataflow_match.py:102
Methodnull
(x)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/examples/python3-grammar.py:299
Methodnull
(x)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/examples/python3-grammar-crlf.py:299
Methodnull
(x)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/examples/python3.8_grammar.py:613
Methodobservation
(self, obs)
Experiments/ToolManipulation/HotPotQA/wrappers.py:32
Methodon_epoch_end
(self, args, state, control, **kwargs)
Experiments/SymbolicReasoning/do_color.py:332
Methodon_epoch_end
(self, args, state, control, **kwargs)
Experiments/SymbolicReasoning/do_penguins.py:324
Methodon_epoch_end
(self, args, state, control, **kwargs)
Experiments/MathematicalReasoning/do_gsm8k.py:325
Methodon_epoch_end
(self, args, state, control, **kwargs)
Experiments/MathematicalReasoning/do_math.py:323
Methodone
()
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/examples/python3.8_grammar.py:274
Methodpack
(self, linear, scales, zeros, g_idx=None)
Experiments/InstructTuning/mmlu/quant/quant_linear.py:526
Methodpos0key1
(*, key)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/examples/python3-grammar.py:259
Methodpos0key1
(*, key)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/examples/python3-grammar-crlf.py:259
Methodpos0key1
(*, key)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/examples/python3.8_grammar.py:554
Methodpos2key2
(p1, p2, *, k1, k2=100)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/examples/python3-grammar.py:261
Methodpos2key2
(p1, p2, *, k1, k2=100)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/examples/python3-grammar-crlf.py:261
Methodpos2key2
(p1, p2, *, k1, k2=100)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/examples/python3.8_grammar.py:556
Methodpos2key2dict
(p1, p2, *, k1=100, k2, **kwarg)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/examples/python3-grammar.py:265
Methodpos2key2dict
(p1, p2, *, k1=100, k2, **kwarg)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/examples/python3-grammar-crlf.py:265
Methodpos2key2dict
(p1, p2, *, k1=100, k2, **kwarg)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/tree-sitter-python/examples/python3.8_grammar.py:560
Functionprefix_exact_match
The `prefix_exact_match` metric is particularly useful in the zero-shot setting, where the model is not given examples of the expected output
Experiments/KnowledgeUtilization/WikiFact/em.py:41
Functionprocess
(data)
Experiments/SymbolicReasoning/do_color.py:485
Functionprocess
(data)
Experiments/SymbolicReasoning/do_penguins.py:479
Functionprocess
(data)
Experiments/MathematicalReasoning/do_gsm8k.py:457
Functionprocess
(data)
Experiments/MathematicalReasoning/do_math.py:467
Methodprocess
( self, data, num_del_examplar=0, pattern_demo="Problem: {}\n
Experiments/SymbolicReasoning/data_process.py:117
Methodprocess
( self, data, num_del_examplar=0, pattern_demo="Problem: {}\nS
Experiments/SymbolicReasoning/data_process.py:285
Methodprocess
( self, data, )
Experiments/SymbolicReasoning/data_process.py:323
Methodprocess
( self, data, )
Experiments/SymbolicReasoning/data_process.py:342
Methodprocess
( self, data, num_del_examplar=0, pattern_demo="Problem: {}\n
Experiments/MathematicalReasoning/data_process.py:117
Methodprocess
( self, data, num_del_examplar=0, pattern_demo="Problem: {}\nS
Experiments/MathematicalReasoning/data_process.py:285
Methodprocess
( self, data, )
Experiments/MathematicalReasoning/data_process.py:323
Methodprocess
( self, data, )
Experiments/MathematicalReasoning/data_process.py:342
Methodprocess_classifier
( self, data, num_del_examplar=0, pattern_demo="Problem: {}\nP
Experiments/SymbolicReasoning/data_process.py:60
Methodprocess_classifier
( self, data, num_del_examplar=0, pattern_demo="Problem: {}\nP
Experiments/MathematicalReasoning/data_process.py:60
Methodprocess_decompose
( self, data, num_del_examplar=0, pattern_demo="Problem: {}\n
Experiments/SymbolicReasoning/data_process.py:138
Methodprocess_decompose
( self, data, num_del_examplar=0, pattern_demo="Problem: {}\n
Experiments/MathematicalReasoning/data_process.py:138
Methodprocess_decompose_wo_cot
( self, data, num_del_examplar=0, pattern_demo="Problem: {}\n
Experiments/SymbolicReasoning/data_process.py:158
Methodprocess_decompose_wo_cot
( self, data, num_del_examplar=0, pattern_demo="Problem: {}\n
Experiments/MathematicalReasoning/data_process.py:158
Functionprocess_entry
(entry, api_key)
Experiments/ToolManipulation/Gorilla/eval/get_llm_responses.py:88
Functionprocess_response
(response, api_database, qa_pairs, ast_database)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/ast_eval_th.py:128
Methodprocess_retrieval
( self, data, num_del_examplar, ret_examplar, patt
Experiments/SymbolicReasoning/data_process.py:38
Methodprocess_retrieval
( self, data, num_del_examplar, ret_examplar, patt
Experiments/MathematicalReasoning/data_process.py:38
Methodprocess_solve_decompose
( self, test_data=None, num_del_examplar=0 )
Experiments/SymbolicReasoning/data_process.py:177
Methodprocess_solve_decompose
( self, test_data=None, num_del_examplar=0 )
Experiments/MathematicalReasoning/data_process.py:177
Methodprocess_solve_decompose_together
( self, test_data=None, num_del_examplar=0 )
Experiments/SymbolicReasoning/data_process.py:203
Methodprocess_solve_decompose_together
( self, test_data=None, num_del_examplar=0 )
Experiments/MathematicalReasoning/data_process.py:203
Methodquantize
(self, x)
Experiments/InstructTuning/mmlu/quant/quantizer.py:128
Functionquasi_exact_match
(gold: str, pred: str)
Experiments/KnowledgeUtilization/WikiFact/em.py:34
Functionquasi_prefix_exact_match
Same thing as `prefix_exact_match` but we normalize the text before checking if the prefix match.
Experiments/KnowledgeUtilization/WikiFact/em.py:62
Functionreplacer
(match)
Experiments/ToolManipulation/Gorilla/eval/eval-scripts/codebleu/parser/utils.py:51
Methodreset
(self, seed=None, return_info=False, options=None, idx=None)
Experiments/ToolManipulation/HotPotQA/wrappers.py:89
Methodreset
(self, seed=None, return_info=False, options=None, idx=None)
Experiments/ToolManipulation/HotPotQA/wrappers.py:214
Functionrms_norm_fwd_fused
( X, # pointer to the input Y, # pointer to the output W, # pointer to the weights stride,
Experiments/InstructTuning/mmlu/quant/triton_norm.py:9
Functionrotate_half_kernel
( qk_seq_ptr, position_ids_ptr, qk_seq_stride, position_ids_batch_stride, seq_len, HEA
Experiments/InstructTuning/mmlu/quant/fused_attn.py:9
Methodrun
(self, prompt: str, **kwargs)
Experiments/InstructTuning/mmlu/modeling.py:70
Methodrun
(self, prompt: str, **kwargs)
Experiments/InstructTuning/mmlu/modeling.py:109
Methodrun
(self, prompt: str, **kwargs)
Experiments/InstructTuning/mmlu/modeling.py:139
Methodrun
(self, prompt: str, **kwargs)
Experiments/InstructTuning/mmlu/modeling.py:181
Methodrun
(self, prompt: str, **kwargs)
Experiments/InstructTuning/mmlu/modeling.py:327
← previousnext →701–800 of 1,088, ranked by callers