Amanda commited on
Commit
449f290
1 Parent(s): 72f4b65

Upload 10 files

Browse files
.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[[:space:]](3).json filter=lfs diff=lfs merge=lfs -text
README (1).md ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ datasets: []
3
+ language: []
4
+ library_name: sentence-transformers
5
+ pipeline_tag: sentence-similarity
6
+ tags:
7
+ - sentence-transformers
8
+ - sentence-similarity
9
+ - feature-extraction
10
+ widget: []
11
+ ---
12
+
13
+ # SentenceTransformer
14
+
15
+ This is a [sentence-transformers](https://www.SBERT.net) model trained. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
16
+
17
+ ## Model Details
18
+
19
+ ### Model Description
20
+ - **Model Type:** Sentence Transformer
21
+ <!-- - **Base model:** [Unknown](https://huggingface.co/unknown) -->
22
+ - **Maximum Sequence Length:** 8192 tokens
23
+ - **Output Dimensionality:** 1024 tokens
24
+ - **Similarity Function:** Cosine Similarity
25
+ <!-- - **Training Dataset:** Unknown -->
26
+ <!-- - **Language:** Unknown -->
27
+ <!-- - **License:** Unknown -->
28
+
29
+ ### Model Sources
30
+
31
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
32
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
33
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
34
+
35
+ ### Full Model Architecture
36
+
37
+ ```
38
+ SentenceTransformer(
39
+ (0): Transformer({'max_seq_length': 8192, 'do_lower_case': False}) with Transformer model: XLMRobertaModel
40
+ (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
41
+ (2): Normalize()
42
+ )
43
+ ```
44
+
45
+ ## Usage
46
+
47
+ ### Direct Usage (Sentence Transformers)
48
+
49
+ First install the Sentence Transformers library:
50
+
51
+ ```bash
52
+ pip install -U sentence-transformers
53
+ ```
54
+
55
+ Then you can load this model and run inference.
56
+ ```python
57
+ from sentence_transformers import SentenceTransformer
58
+
59
+ # Download from the 🤗 Hub
60
+ model = SentenceTransformer("sentence_transformers_model_id")
61
+ # Run inference
62
+ sentences = [
63
+ 'The weather is lovely today.',
64
+ "It's so sunny outside!",
65
+ 'He drove to the stadium.',
66
+ ]
67
+ embeddings = model.encode(sentences)
68
+ print(embeddings.shape)
69
+ # [3, 1024]
70
+
71
+ # Get the similarity scores for the embeddings
72
+ similarities = model.similarity(embeddings, embeddings)
73
+ print(similarities.shape)
74
+ # [3, 3]
75
+ ```
76
+
77
+ <!--
78
+ ### Direct Usage (Transformers)
79
+
80
+ <details><summary>Click to see the direct usage in Transformers</summary>
81
+
82
+ </details>
83
+ -->
84
+
85
+ <!--
86
+ ### Downstream Usage (Sentence Transformers)
87
+
88
+ You can finetune this model on your own dataset.
89
+
90
+ <details><summary>Click to expand</summary>
91
+
92
+ </details>
93
+ -->
94
+
95
+ <!--
96
+ ### Out-of-Scope Use
97
+
98
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
99
+ -->
100
+
101
+ <!--
102
+ ## Bias, Risks and Limitations
103
+
104
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
105
+ -->
106
+
107
+ <!--
108
+ ### Recommendations
109
+
110
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
111
+ -->
112
+
113
+ ## Training Details
114
+
115
+ ### Framework Versions
116
+ - Python: 3.8.10
117
+ - Sentence Transformers: 3.0.1
118
+ - Transformers: 4.43.4
119
+ - PyTorch: 1.14.0a0+410ce96
120
+ - Accelerate: 0.33.0
121
+ - Datasets: 2.20.0
122
+ - Tokenizers: 0.19.1
123
+
124
+ ## Citation
125
+
126
+ ### BibTeX
127
+
128
+ <!--
129
+ ## Glossary
130
+
131
+ *Clearly define terms in order to be accessible across audiences.*
132
+ -->
133
+
134
+ <!--
135
+ ## Model Card Authors
136
+
137
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
138
+ -->
139
+
140
+ <!--
141
+ ## Model Card Contact
142
+
143
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
144
+ -->
config (6).json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "resultado_modelo",
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": 1024,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 8194,
17
+ "model_type": "xlm-roberta",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 24,
20
+ "output_past": true,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.43.4",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 250002
28
+ }
config_sentence_transformers (3).json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.0.1",
4
+ "transformers": "4.43.4",
5
+ "pytorch": "1.14.0a0+410ce96"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null,
9
+ "similarity_fn_name": null
10
+ }
model (3).safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef57171b63b6b465b9efa16e7e81013cbba7e067a729db2118e17e392c6556ba
3
+ size 2271064456
modules (3).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 (3).json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 8192,
3
+ "do_lower_case": false
4
+ }
sentencepiece.bpe (3).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 (3).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 (3).json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bf8afbfd11306bd872018c53bfdf2e160a56f8edbcf49933324404791c148d3
3
+ size 17082900
tokenizer_config (3).json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 8192,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "sp_model_kwargs": {},
53
+ "tokenizer_class": "XLMRobertaTokenizer",
54
+ "unk_token": "<unk>"
55
+ }