intfloat/multilingual-e5-base
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: intfloat/multilingual-e5-base
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-14 13:23:41 +08:00
commit efd828d4d6
23 changed files with 19504 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
.eval_results/ArguAna.yaml Normal file
View File

@@ -0,0 +1,20 @@
- dataset:
id: mteb/arguana
task_id: ArguAna_default_test
revision: c22ab2a51041ffd869aaddef7af8d8215647e41a
value: 44.206
notes: Obtained using MTEB v1.12.75
source:
url: https://github.com/embeddings-benchmark/mteb/
name: Obtained using MTEB v1.12.75
user: mteb
- dataset:
id: mteb/arguana
task_id: ArguAna
revision: c22ab2a51041ffd869aaddef7af8d8215647e41a
value: 44.206
notes: Obtained using MTEB v1.12.75
source:
url: https://github.com/embeddings-benchmark/mteb/
name: Obtained using MTEB v1.12.75
user: mteb

35
.gitattributes vendored Normal file
View File

@@ -0,0 +1,35 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
tokenizer.json filter=lfs diff=lfs merge=lfs -text

7
1_Pooling/config.json Normal file
View File

@@ -0,0 +1,7 @@
{
"word_embedding_dimension": 768,
"pooling_mode_cls_token": false,
"pooling_mode_mean_tokens": true,
"pooling_mode_max_tokens": false,
"pooling_mode_mean_sqrt_len_tokens": false
}

6949
README.md Normal file
View File

File diff suppressed because it is too large Load Diff

28
config.json Normal file
View File

@@ -0,0 +1,28 @@
{
"_name_or_path": "tmp/",
"architectures": [
"XLMRobertaModel"
],
"attention_probs_dropout_prob": 0.1,
"bos_token_id": 0,
"classifier_dropout": null,
"eos_token_id": 2,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"initializer_range": 0.02,
"intermediate_size": 3072,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 514,
"model_type": "xlm-roberta",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"output_past": true,
"pad_token_id": 1,
"position_embedding_type": "absolute",
"torch_dtype": "float32",
"transformers_version": "4.29.0.dev0",
"type_vocab_size": 1,
"use_cache": true,
"vocab_size": 250002
}

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a18a44fad1d0b46ded15928144138cff1135d5cc8233bdd90be5f18822de09a7
size 1112201288

20
modules.json Normal file
View File

@@ -0,0 +1,20 @@
[
{
"idx": 0,
"name": "0",
"path": "",
"type": "sentence_transformers.models.Transformer"
},
{
"idx": 1,
"name": "1",
"path": "1_Pooling",
"type": "sentence_transformers.models.Pooling"
},
{
"idx": 2,
"name": "2",
"path": "2_Normalize",
"type": "sentence_transformers.models.Normalize"
}
]

27
onnx/config.json Normal file
View File

@@ -0,0 +1,27 @@
{
"_name_or_path": "intfloat/multilingual-e5-base",
"architectures": [
"XLMRobertaModel"
],
"attention_probs_dropout_prob": 0.1,
"bos_token_id": 0,
"classifier_dropout": null,
"eos_token_id": 2,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"initializer_range": 0.02,
"intermediate_size": 3072,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 514,
"model_type": "xlm-roberta",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"output_past": true,
"pad_token_id": 1,
"position_embedding_type": "absolute",
"transformers_version": "4.30.2",
"type_vocab_size": 1,
"use_cache": true,
"vocab_size": 250002
}

3
onnx/model.onnx Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:84a4d426f7e87a6bf5bf195f0bae2c4a7d15f675b23ca96f42fab8326d7a77aa
size 1110059084

3
onnx/model_O4.onnx Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f60256a833caee5c75a3903e589116752ee016ca7bc16f9b96e4db09984c5703
size 554948118

3
onnx/model_qint8_avx512_vnni.onnx Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2523551878658b305550d8759443822dbfda9ed9c8012ef2c354ba2c5b9de503
size 278686411

3
onnx/sentencepiece.bpe.model Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
size 5069051

15
onnx/special_tokens_map.json Normal file
View File

@@ -0,0 +1,15 @@
{
"bos_token": "<s>",
"cls_token": "<s>",
"eos_token": "</s>",
"mask_token": {
"content": "<mask>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": "<pad>",
"sep_token": "</s>",
"unk_token": "<unk>"
}

3
onnx/tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
size 17082660

19
onnx/tokenizer_config.json Normal file
View File

@@ -0,0 +1,19 @@
{
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "<s>",
"eos_token": "</s>",
"mask_token": {
"__type": "AddedToken",
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 512,
"pad_token": "<pad>",
"sep_token": "</s>",
"tokenizer_class": "XLMRobertaTokenizer",
"unk_token": "<unk>"
}

3
openvino/openvino_model.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:116c03a2814daff8b5dd1894edef0405cffa552b6df71f7dd933a451c8aa0ea4
size 1109816496

12316
openvino/openvino_model.xml Normal file
View File

File diff suppressed because it is too large Load Diff

3
pytorch_model.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f061cb7641880f52895cbacab7c4ab39b0844e2e6b73794f2798de460d9fa418
size 1112242989

4
sentence_bert_config.json Normal file
View File

@@ -0,0 +1,4 @@
{
"max_seq_length": 512,
"do_lower_case": false
}

3
sentencepiece.bpe.model Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
size 5069051

15
special_tokens_map.json Normal file
View File

@@ -0,0 +1,15 @@
{
"bos_token": "<s>",
"cls_token": "<s>",
"eos_token": "</s>",
"mask_token": {
"content": "<mask>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": "<pad>",
"sep_token": "</s>",
"unk_token": "<unk>"
}

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
size 17082660

19
tokenizer_config.json Normal file
View File

@@ -0,0 +1,19 @@
{
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "<s>",
"eos_token": "</s>",
"mask_token": {
"__type": "AddedToken",
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 512,
"pad_token": "<pad>",
"sep_token": "</s>",
"tokenizer_class": "XLMRobertaTokenizer",
"unk_token": "<unk>"
}