初始化项目,由ModelHub XC社区提供模型

Model: shibing624/text2vec-bge-large-chinese
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-14 12:53:42 +08:00
commit 7804d022b1
18 changed files with 85287 additions and 0 deletions

40
onnx/config.json Normal file
View File

@@ -0,0 +1,40 @@
{
"_attn_implementation_autoset": true,
"architectures": [
"BertModel"
],
"attention_probs_dropout_prob": 0.1,
"bos_token_id": 0,
"classifier_dropout": null,
"directionality": "bidi",
"eos_token_id": 2,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 1024,
"id2label": {
"0": "LABEL_0"
},
"initializer_range": 0.02,
"intermediate_size": 4096,
"label2id": {
"LABEL_0": 0
},
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "bert",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"output_past": true,
"pad_token_id": 0,
"pooler_fc_size": 768,
"pooler_num_attention_heads": 12,
"pooler_num_fc_layers": 3,
"pooler_size_per_head": 128,
"pooler_type": "first_token_transform",
"position_embedding_type": "absolute",
"torch_dtype": "float32",
"transformers_version": "4.51.3",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 21128
}

3
onnx/model.onnx Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:15714229468fee8abaf63499d512fa49ebfa2f8089a60c8823e65ec3ea19404b
size 1298440934

View File

@@ -0,0 +1,37 @@
{
"cls_token": {
"content": "[CLS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"mask_token": {
"content": "[MASK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"sep_token": {
"content": "[SEP]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

21292
onnx/tokenizer.json Normal file

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,65 @@
{
"added_tokens_decoder": {
"0": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"101": {
"content": "[CLS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"102": {
"content": "[SEP]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"103": {
"content": "[MASK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"extra_special_tokens": {},
"mask_token": "[MASK]",
"max_length": 256,
"model_max_length": 512,
"never_split": null,
"pad_to_multiple_of": null,
"pad_token": "[PAD]",
"pad_token_type_id": 0,
"padding_side": "right",
"sep_token": "[SEP]",
"stride": 0,
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "[UNK]"
}

21128
onnx/vocab.txt Normal file

File diff suppressed because it is too large Load Diff