Upload 12 files
Browse files- .gitattributes +1 -0
- 1_Pooling/config.json +10 -0
- README.md +92 -0
- config.json +28 -0
- config_sentence_transformers.json +9 -0
- eval/Information-Retrieval_evaluation_results.csv +9 -0
- model.safetensors +3 -0
- modules.json +20 -0
- sentence_bert_config.json +4 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +3 -0
- tokenizer_config.json +54 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
1_Pooling/config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"word_embedding_dimension": 768,
|
3 |
+
"pooling_mode_cls_token": false,
|
4 |
+
"pooling_mode_mean_tokens": true,
|
5 |
+
"pooling_mode_max_tokens": false,
|
6 |
+
"pooling_mode_mean_sqrt_len_tokens": false,
|
7 |
+
"pooling_mode_weightedmean_tokens": false,
|
8 |
+
"pooling_mode_lasttoken": false,
|
9 |
+
"include_prompt": true
|
10 |
+
}
|
README.md
ADDED
@@ -0,0 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: sentence-transformers
|
3 |
+
pipeline_tag: sentence-similarity
|
4 |
+
tags:
|
5 |
+
- sentence-transformers
|
6 |
+
- feature-extraction
|
7 |
+
- sentence-similarity
|
8 |
+
|
9 |
+
---
|
10 |
+
|
11 |
+
# {MODEL_NAME}
|
12 |
+
|
13 |
+
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
|
14 |
+
|
15 |
+
<!--- Describe your model here -->
|
16 |
+
|
17 |
+
## Usage (Sentence-Transformers)
|
18 |
+
|
19 |
+
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
|
20 |
+
|
21 |
+
```
|
22 |
+
pip install -U sentence-transformers
|
23 |
+
```
|
24 |
+
|
25 |
+
Then you can use the model like this:
|
26 |
+
|
27 |
+
```python
|
28 |
+
from sentence_transformers import SentenceTransformer
|
29 |
+
sentences = ["This is an example sentence", "Each sentence is converted"]
|
30 |
+
|
31 |
+
model = SentenceTransformer('{MODEL_NAME}')
|
32 |
+
embeddings = model.encode(sentences)
|
33 |
+
print(embeddings)
|
34 |
+
```
|
35 |
+
|
36 |
+
|
37 |
+
|
38 |
+
## Evaluation Results
|
39 |
+
|
40 |
+
<!--- Describe how your model was evaluated -->
|
41 |
+
|
42 |
+
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
|
43 |
+
|
44 |
+
|
45 |
+
## Training
|
46 |
+
The model was trained with the parameters:
|
47 |
+
|
48 |
+
**DataLoader**:
|
49 |
+
|
50 |
+
`torch.utils.data.dataloader.DataLoader` of length 59 with parameters:
|
51 |
+
```
|
52 |
+
{'batch_size': 10, 'sampler': 'torch.utils.data.sampler.SequentialSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
|
53 |
+
```
|
54 |
+
|
55 |
+
**Loss**:
|
56 |
+
|
57 |
+
`sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
|
58 |
+
```
|
59 |
+
{'scale': 20.0, 'similarity_fct': 'cos_sim'}
|
60 |
+
```
|
61 |
+
|
62 |
+
Parameters of the fit()-Method:
|
63 |
+
```
|
64 |
+
{
|
65 |
+
"epochs": 4,
|
66 |
+
"evaluation_steps": 50,
|
67 |
+
"evaluator": "sentence_transformers.evaluation.InformationRetrievalEvaluator.InformationRetrievalEvaluator",
|
68 |
+
"max_grad_norm": 1,
|
69 |
+
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
|
70 |
+
"optimizer_params": {
|
71 |
+
"lr": 2e-05
|
72 |
+
},
|
73 |
+
"scheduler": "WarmupLinear",
|
74 |
+
"steps_per_epoch": null,
|
75 |
+
"warmup_steps": 23,
|
76 |
+
"weight_decay": 0.01
|
77 |
+
}
|
78 |
+
```
|
79 |
+
|
80 |
+
|
81 |
+
## Full Model Architecture
|
82 |
+
```
|
83 |
+
SentenceTransformer(
|
84 |
+
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: XLMRobertaModel
|
85 |
+
(1): Pooling({'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, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
|
86 |
+
(2): Normalize()
|
87 |
+
)
|
88 |
+
```
|
89 |
+
|
90 |
+
## Citing & Authors
|
91 |
+
|
92 |
+
<!--- Describe where people can find more information -->
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "intfloat/multilingual-e5-base",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 514,
|
17 |
+
"model_type": "xlm-roberta",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"output_past": true,
|
21 |
+
"pad_token_id": 1,
|
22 |
+
"position_embedding_type": "absolute",
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.39.3",
|
25 |
+
"type_vocab_size": 1,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 250002
|
28 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "2.6.1",
|
4 |
+
"transformers": "4.39.3",
|
5 |
+
"pytorch": "2.3.0+cpu"
|
6 |
+
},
|
7 |
+
"prompts": {},
|
8 |
+
"default_prompt_name": null
|
9 |
+
}
|
eval/Information-Retrieval_evaluation_results.csv
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
epoch,steps,cos_sim-Accuracy@1,cos_sim-Accuracy@3,cos_sim-Accuracy@5,cos_sim-Accuracy@10,cos_sim-Precision@1,cos_sim-Recall@1,cos_sim-Precision@3,cos_sim-Recall@3,cos_sim-Precision@5,cos_sim-Recall@5,cos_sim-Precision@10,cos_sim-Recall@10,cos_sim-MRR@10,cos_sim-NDCG@10,cos_sim-MAP@100,dot_score-Accuracy@1,dot_score-Accuracy@3,dot_score-Accuracy@5,dot_score-Accuracy@10,dot_score-Precision@1,dot_score-Recall@1,dot_score-Precision@3,dot_score-Recall@3,dot_score-Precision@5,dot_score-Recall@5,dot_score-Precision@10,dot_score-Recall@10,dot_score-MRR@10,dot_score-NDCG@10,dot_score-MAP@100
|
2 |
+
0,50,0.6391752577319587,0.7989690721649485,0.8470790378006873,0.8900343642611683,0.6391752577319587,0.6391752577319587,0.2663230240549828,0.7989690721649485,0.1694158075601374,0.8470790378006873,0.08900343642611683,0.8900343642611683,0.7308153330060548,0.7698315629602112,0.7349608246472122,0.6391752577319587,0.7989690721649485,0.8470790378006873,0.8900343642611683,0.6391752577319587,0.6391752577319587,0.2663230240549828,0.7989690721649485,0.1694158075601374,0.8470790378006873,0.08900343642611683,0.8900343642611683,0.7308153330060548,0.7698315629602112,0.7349608246472122
|
3 |
+
0,-1,0.6649484536082474,0.8127147766323024,0.8608247422680413,0.9020618556701031,0.6649484536082474,0.6649484536082474,0.2709049255441008,0.8127147766323024,0.17216494845360822,0.8608247422680413,0.0902061855670103,0.9020618556701031,0.7477758686521572,0.7853586074809755,0.7514607649671707,0.6649484536082474,0.8127147766323024,0.8608247422680413,0.9020618556701031,0.6649484536082474,0.6649484536082474,0.2709049255441008,0.8127147766323024,0.17216494845360822,0.8608247422680413,0.0902061855670103,0.9020618556701031,0.7477758686521572,0.7853586074809755,0.7514607649671707
|
4 |
+
1,50,0.7010309278350515,0.8487972508591065,0.8900343642611683,0.915807560137457,0.7010309278350515,0.7010309278350515,0.2829324169530355,0.8487972508591065,0.17800687285223366,0.8900343642611683,0.0915807560137457,0.915807560137457,0.7825499099983633,0.8154809950834685,0.7855589868510762,0.7010309278350515,0.8487972508591065,0.8900343642611683,0.915807560137457,0.7010309278350515,0.7010309278350515,0.2829324169530355,0.8487972508591065,0.17800687285223366,0.8900343642611683,0.0915807560137457,0.915807560137457,0.7825499099983633,0.8154809950834685,0.7855589868510762
|
5 |
+
1,-1,0.7044673539518901,0.8591065292096219,0.8917525773195877,0.915807560137457,0.7044673539518901,0.7044673539518901,0.2863688430698739,0.8591065292096219,0.1783505154639175,0.8917525773195877,0.0915807560137457,0.915807560137457,0.787294087165221,0.8191872218183971,0.7903220393283484,0.7044673539518901,0.8591065292096219,0.8917525773195877,0.915807560137457,0.7044673539518901,0.7044673539518901,0.2863688430698739,0.8591065292096219,0.1783505154639175,0.8917525773195877,0.0915807560137457,0.915807560137457,0.787294087165221,0.8191872218183971,0.7903220393283484
|
6 |
+
2,50,0.7164948453608248,0.8694158075601375,0.8986254295532646,0.915807560137457,0.7164948453608248,0.7164948453608248,0.28980526918671246,0.8694158075601375,0.17972508591065292,0.8986254295532646,0.0915807560137457,0.915807560137457,0.7962724322260402,0.826095148308153,0.7995469606673189,0.7164948453608248,0.8694158075601375,0.8986254295532646,0.915807560137457,0.7164948453608248,0.7164948453608248,0.28980526918671246,0.8694158075601375,0.17972508591065292,0.8986254295532646,0.0915807560137457,0.915807560137457,0.7962724322260402,0.826095148308153,0.7995469606673189
|
7 |
+
2,-1,0.7199312714776632,0.8711340206185567,0.8951890034364262,0.915807560137457,0.7199312714776632,0.7199312714776632,0.29037800687285226,0.8711340206185567,0.1790378006872852,0.8951890034364262,0.0915807560137457,0.915807560137457,0.7977649593628973,0.8271589378763345,0.8010179808893677,0.7199312714776632,0.8711340206185567,0.8951890034364262,0.915807560137457,0.7199312714776632,0.7199312714776632,0.29037800687285226,0.8711340206185567,0.1790378006872852,0.8951890034364262,0.0915807560137457,0.915807560137457,0.7977649593628973,0.8271589378763345,0.8010179808893677
|
8 |
+
3,50,0.7199312714776632,0.8745704467353952,0.8951890034364262,0.9140893470790378,0.7199312714776632,0.7199312714776632,0.2915234822451317,0.8745704467353952,0.1790378006872852,0.8951890034364262,0.09140893470790376,0.9140893470790378,0.7985177003218239,0.8274291887612075,0.8019395117248479,0.7199312714776632,0.8745704467353952,0.8951890034364262,0.9140893470790378,0.7199312714776632,0.7199312714776632,0.2915234822451317,0.8745704467353952,0.1790378006872852,0.8951890034364262,0.09140893470790376,0.9140893470790378,0.7985177003218239,0.8274291887612075,0.8019395117248479
|
9 |
+
3,-1,0.7199312714776632,0.8762886597938144,0.8951890034364262,0.9140893470790378,0.7199312714776632,0.7199312714776632,0.2920962199312715,0.8762886597938144,0.1790378006872852,0.8951890034364262,0.09140893470790376,0.9140893470790378,0.7986608847433587,0.8275483012043804,0.8020821698587838,0.7199312714776632,0.8762886597938144,0.8951890034364262,0.9140893470790378,0.7199312714776632,0.7199312714776632,0.2920962199312715,0.8762886597938144,0.1790378006872852,0.8951890034364262,0.09140893470790376,0.9140893470790378,0.7986608847433587,0.8275483012043804,0.8020821698587838
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce26da7fb6b5e469877c098e4c74e1ba4eb551e91d8f36395d6ed39ce27ac5a3
|
3 |
+
size 1112197096
|
modules.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[
|
2 |
+
{
|
3 |
+
"idx": 0,
|
4 |
+
"name": "0",
|
5 |
+
"path": "",
|
6 |
+
"type": "sentence_transformers.models.Transformer"
|
7 |
+
},
|
8 |
+
{
|
9 |
+
"idx": 1,
|
10 |
+
"name": "1",
|
11 |
+
"path": "1_Pooling",
|
12 |
+
"type": "sentence_transformers.models.Pooling"
|
13 |
+
},
|
14 |
+
{
|
15 |
+
"idx": 2,
|
16 |
+
"name": "2",
|
17 |
+
"path": "2_Normalize",
|
18 |
+
"type": "sentence_transformers.models.Normalize"
|
19 |
+
}
|
20 |
+
]
|
sentence_bert_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"max_seq_length": 512,
|
3 |
+
"do_lower_case": false
|
4 |
+
}
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
3 |
+
size 5069051
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1cc44ad7faaeec47241864835473fd5403f2da94673f3f764a77ebcb0a803ec
|
3 |
+
size 17083009
|
tokenizer_config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"250001": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"bos_token": "<s>",
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "<s>",
|
47 |
+
"eos_token": "</s>",
|
48 |
+
"mask_token": "<mask>",
|
49 |
+
"model_max_length": 512,
|
50 |
+
"pad_token": "<pad>",
|
51 |
+
"sep_token": "</s>",
|
52 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
53 |
+
"unk_token": "<unk>"
|
54 |
+
}
|