MCPcopy Create free account

hub / github.com/TencentCloudADP/youtu-embedding / functions

Functions191 in github.com/TencentCloudADP/youtu-embedding

↓ 7 callersFunctionsetLocaleCookie
(response: NextResponse, locale: string)
docs/middleware.ts:32
↓ 6 callersMethodencode
(self, features)
training/CoDiEmb/train/model.py:133
↓ 6 callersMethodpooling
(self, hidden_state: torch.Tensor, attention_mask: torch.Tensor = None, recast: bool = False)
training/CoDiEmb/train/model.py:233
↓ 4 callersFunctionbuildDocsPath
(locale: string, rest: string[] = [])
docs/middleware.ts:39
↓ 3 callersMethod_gather_tensor
(t: torch.Tensor)
training/CoDiEmb/train/loss.py:132
↓ 3 callersMethod_prepare_texts
A centralized method to prepare texts by adding model-specific prefixes (instructions) and suffixes.
training/CoDiEmb/test/cmteb_dres_model.py:68
↓ 3 callersMethodcompute_similarity
(q_reps: torch.Tensor, p_reps: torch.Tensor)
training/CoDiEmb/train/loss.py:126
↓ 3 callersMethodget_embedding
(self, sentences: List[str], instruction="", **kwargs)
training/CoDiEmb/test/cmteb_dres_model.py:85
↓ 2 callersMethod__init__
Args: eps (float): A small epsilon value to ensure numerical stability and handle comparisons, e.g., to
training/CoDiEmb/train/loss.py:239
↓ 2 callersMethod_dist_gather_tensor
(self, t: torch.Tensor)
training/CoDiEmb/train/loss.py:165
↓ 2 callersMethod_dist_gather_tensor
(self, t: torch.Tensor)
training/CoDiEmb/train/loss.py:219
↓ 2 callersMethod_dist_gather_tensor
(self, t: torch.Tensor)
training/CoDiEmb/train/loss.py:315
↓ 2 callersMethod_do_it_first
(self, first)
training/CoDiEmb/train/utils.py:25
↓ 2 callersFunctionbaseOptions
(locale: string)
docs/app/layout.config.tsx:13
↓ 2 callersFunctionbuild_instruction_prefix
(model_name: str, instruction: str = "")
training/CoDiEmb/test/eval_cmteb.py:62
↓ 2 callersMethodbuild_query
Assemble instruction and text, and return both the full text and instruction length. Returns: (full_text: str, instruction_len: int)
training/CoDiEmb/train/data.py:140
↓ 2 callersMethodcreate_text_mask
Create precise text_mask based on offset_mapping and instruction character lengths. 1 indicates text token, 0 indicates instruction/p
training/CoDiEmb/train/data.py:214
↓ 2 callersMethodencode
(self, sentences_batch, instruction)
test_transformers_local.py:47
↓ 2 callersMethodencode
(self, sentences_batch, instruction)
test_transformers_online_macos.py:46
↓ 2 callersMethodencode
(self, sentences_batch, instruction)
test_transformers_online_cuda.py:38
↓ 2 callersMethodencode
(self, sentences_batch, instruction)
usage/infer_llm_embedding.py:50
↓ 2 callersFunctiongenerateI18nUrl
(targetLocale: string, currentPathname: string)
docs/lib/i18n-utils.ts:4
↓ 2 callersFunctionopenDemo
(title: string, url: string)
docs/components/home/LandingShowcase.tsx:99
↓ 2 callersFunctionprocess_dataset
(data_args, training_args, num_samples, ds_name_to_samples, task_data, tokenizer=None)
training/CoDiEmb/train/run.py:103
↓ 2 callersFunctionrenderPage
(page: any)
docs/app/docs/[lang]/[[...slug]]/page.tsx:37
↓ 2 callersMethodset_epoch
(self, epoch)
training/CoDiEmb/train/run.py:466
↓ 2 callersMethodwait_for_everyone
(self)
training/CoDiEmb/train/utils.py:22
↓ 2 callersFunctionwrappeed_callable
()
training/CoDiEmb/train/utils.py:61
↓ 1 callersMethod_get_average_ranks
(self, x: torch.Tensor)
training/CoDiEmb/train/loss.py:193
↓ 1 callersMethod_loss_ir
( self, q_reps: torch.Tensor, p_reps: torch.Tensor )
training/CoDiEmb/train/loss.py:81
↓ 1 callersMethod_loss_sts
( self, q_reps: torch.Tensor, p_reps: torch.Tensor, y: Optional[torch.Tensor]
training/CoDiEmb/train/loss.py:55
↓ 1 callersMethod_print_debug_info
(self)
training/CoDiEmb/train/sampler.py:326
↓ 1 callersFunctionanalyze_retrieval_results
读取指定文件夹中的所有 .json 文件,提取信息并计算总分和平均分。 :param folder_path: 存放 .json 文件的文件夹路径
training/CoDiEmb/test/result/get_ir_ndcg.py:5
↓ 1 callersFunctionanalyze_sts_results
读取指定文件夹中的所有 STS 任务 .json 文件,提取 Spearman 相关系数,并计算总分和平均分。 此版本会优先查找 "validation" 字段,如果找不到,则会查找 "test" 字段。 :param folder_path: 存放 .json 文件的
training/CoDiEmb/test/result/get_sts_spearman.py:4
↓ 1 callersFunctionargs_to_dtype
(args)
training/CoDiEmb/train/run.py:28
↓ 1 callersFunctionbroadcast_object_list
(object_list)
training/CoDiEmb/train/utils.py:45
↓ 1 callersFunctionbuildCategoryLinks
( articles: RawArticleCard[], lang: LanguageKey, )
docs/app/[lang]/(home)/page.tsx:211
↓ 1 callersMethodbuild_passage
Assemble instruction and text, and return both the full text and instruction length. Returns: (full_text: str, instruction_len: int)
training/CoDiEmb/train/data.py:178
↓ 1 callersFunctionbuild_passage_instruction_prefix
(model_name: str, instruction: str = "")
training/CoDiEmb/test/eval_cmteb.py:79
↓ 1 callersMethodcompute_similarity
(self, queries, passages)
test_transformers_local.py:97
↓ 1 callersMethodcompute_similarity
(self, queries, passages)
test_transformers_online_macos.py:96
↓ 1 callersMethodcompute_similarity
(self, queries, passages)
test_transformers_online_cuda.py:86
↓ 1 callersMethodcompute_similarity
(self, queries, passages)
usage/infer_llm_embedding.py:98
↓ 1 callersMethodcompute_similarity_for_vectors
(self, q_reps, p_reps)
test_transformers_local.py:92
↓ 1 callersMethodcompute_similarity_for_vectors
(self, q_reps, p_reps)
test_transformers_online_macos.py:91
↓ 1 callersMethodcompute_similarity_for_vectors
(self, q_reps, p_reps)
test_transformers_online_cuda.py:81
↓ 1 callersMethodcompute_similarity_for_vectors
(self, q_reps, p_reps)
usage/infer_llm_embedding.py:93
↓ 1 callersMethoddisplay_results
Display similarity results in a detailed visual format
test_transformers_local.py:104
↓ 1 callersFunctionencode
(client, inputs, is_query=False)
usage/tencent_cloud_api.py:15
↓ 1 callersMethodencode_passages
(self, passages)
test_transformers_local.py:87
↓ 1 callersMethodencode_passages
(self, passages)
test_transformers_online_macos.py:86
↓ 1 callersMethodencode_passages
(self, passages)
test_transformers_online_cuda.py:76
↓ 1 callersMethodencode_passages
(self, passages)
usage/infer_llm_embedding.py:88
↓ 1 callersMethodencode_queries
(self, queries)
test_transformers_local.py:82
↓ 1 callersMethodencode_queries
(self, queries)
test_transformers_online_macos.py:81
↓ 1 callersMethodencode_queries
(self, queries)
test_transformers_online_cuda.py:71
↓ 1 callersMethodencode_queries
(self, queries)
usage/infer_llm_embedding.py:83
↓ 1 callersMethodencode_with_multi_layer_loss
(self, features)
training/CoDiEmb/train/model.py:75
↓ 1 callersMethodencode_wo_multi_layer_loss
(self, features)
training/CoDiEmb/train/model.py:107
↓ 1 callersFunctionfilter_too_long_instructions
(tokenizer, dataset, query_max_len, passage_max_len)
training/CoDiEmb/train/run.py:36
↓ 1 callersFunctionformatBaseUrl
(url: string)
docs/app/sitemap.ts:12
↓ 1 callersFunctionformatCategoryLabel
(key: string, fallback: string)
docs/app/[lang]/(home)/page.tsx:132
↓ 1 callersFunctionformatRelativeUpdate
(timestamp: number, lang: LanguageKey)
docs/app/[lang]/(home)/page.tsx:137
↓ 1 callersFunctiongetArticles
(lang: LanguageKey)
docs/app/[lang]/(home)/page.tsx:165
↓ 1 callersFunctiongetAssetPath
(path: string)
docs/lib/utils.ts:11
↓ 1 callersFunctiongetMDXComponents
(components?: MDXComponents)
docs/mdx-components.tsx:6
↓ 1 callersMethodget_all_dataset_batches
(self, generator)
training/CoDiEmb/train/sampler.py:79
↓ 1 callersFunctionget_args
()
training/CoDiEmb/test/eval_cmteb.py:184
↓ 1 callersMethodget_chunks
(self, global_idxs, ds_indices_per_dataset_chunks)
training/CoDiEmb/train/sampler.py:203
↓ 1 callersMethodget_negatives
(self, data_item)
training/CoDiEmb/train/data.py:80
↓ 1 callersMethodget_positives
(self, data_item)
training/CoDiEmb/train/data.py:62
↓ 1 callersFunctionget_tasks
(names: list[str] | None, languages: list[str] | None = None, benchmark: str | None = None)
evaluation/run_mteb.py:217
↓ 1 callersFunctionloadMermaid
()
docs/components/mdx/mermaid.tsx:21
↓ 1 callersFunctionload_ir_train_data
(data_args, training_args, num_samples, ds_name_to_samples, tokenizer=None)
training/CoDiEmb/train/run.py:164
↓ 1 callersFunctionload_model
(args)
training/CoDiEmb/test/eval_cmteb.py:93
↓ 1 callersFunctionload_sts_train_data
(data_args, training_args, num_samples, ds_name_to_samples, tokenizer=None)
training/CoDiEmb/train/run.py:179
↓ 1 callersFunctionload_train_data
(data_args, training_args, tokenizer=None)
training/CoDiEmb/train/run.py:194
↓ 1 callersFunctionmain
()
test_transformers_local.py:151
↓ 1 callersFunctionmain
()
training/CoDiEmb/test/eval_cmteb.py:198
↓ 1 callersFunctionmain
()
training/CoDiEmb/test/result/get_sts_spearman.py:50
↓ 1 callersFunctionmain
()
training/CoDiEmb/test/result/get_ir_ndcg.py:44
↓ 1 callersFunctionmain
()
training/CoDiEmb/train/run.py:226
↓ 1 callersFunctionmain
()
usage/infer_llm_embedding.py:106
↓ 1 callersFunctionmain
()
evaluation/run_mteb.py:275
↓ 1 callersMethodmean_pooling
(self, hidden_state, attention_mask)
test_transformers_local.py:40
↓ 1 callersMethodmean_pooling
(self, hidden_state, attention_mask)
test_transformers_online_macos.py:39
↓ 1 callersMethodmean_pooling
(self, hidden_state, attention_mask)
test_transformers_online_cuda.py:31
↓ 1 callersMethodmean_pooling
(self, hidden_state, attention_mask)
training/CoDiEmb/test/cmteb_dres_model.py:177
↓ 1 callersMethodmean_pooling
(self, hidden_state, attention_mask)
usage/infer_llm_embedding.py:43
↓ 1 callersFunctionnormalizeLanguage
(lang: string)
docs/app/[lang]/(home)/page.tsx:90
↓ 1 callersFunctionnormalize_dataset_features
(dataset)
training/CoDiEmb/train/run.py:55
↓ 1 callersFunctionone_by_one
()
training/CoDiEmb/train/utils.py:67
↓ 1 callersFunctionoverlap
()
training/CoDiEmb/train/utils.py:82
↓ 1 callersMethodprocess_passages
(self, passage_groups, task_types)
training/CoDiEmb/train/data.py:233
↓ 1 callersFunctionrenderChart
()
docs/components/mdx/mermaid.tsx:29
↓ 1 callersFunctionresolveLocale
(request: NextRequest)
docs/middleware.ts:9
↓ 1 callersFunctionresolveMTime
(relativePath: string)
docs/app/[lang]/(home)/page.tsx:111
↓ 1 callersFunctionresolveRelativePath
(page: ReturnType<typeof source.getPages>[number])
docs/app/[lang]/(home)/page.tsx:104
↓ 1 callersFunctionrun_eval
(model, tasks: list, args: EvalArguments, **kwargs)
evaluation/run_mteb.py:235
↓ 1 callersFunctionset_instruction
(model, task, args)
training/CoDiEmb/test/eval_cmteb.py:155
next →1–100 of 191, ranked by callers