Add SetFit model
Browse files- .gitattributes +1 -0
- 1_Pooling/config.json +9 -0
- README.md +236 -0
- config.json +28 -0
- config_sentence_transformers.json +7 -0
- config_setfit.json +4 -0
- model.safetensors +3 -0
- model_head.pkl +3 -0
- modules.json +20 -0
- sentence_bert_config.json +4 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +15 -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 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"word_embedding_dimension": 1024,
|
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 |
+
}
|
README.md
ADDED
@@ -0,0 +1,236 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: setfit
|
3 |
+
tags:
|
4 |
+
- setfit
|
5 |
+
- sentence-transformers
|
6 |
+
- text-classification
|
7 |
+
- generated_from_setfit_trainer
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
widget:
|
11 |
+
- text: Why is KOF losing share in Cuernavaca Colas MS RET Original?
|
12 |
+
- text: Are there any whitespaces in terms of flavor for KOF within CSD Sabores?
|
13 |
+
- text: What is the trend of KOF"s market share in Colas SS in Cuernavaca from 2019
|
14 |
+
to YTD 2023?
|
15 |
+
- text: Which categories have seen the some of the highest Share losses for KOF in
|
16 |
+
Cuernavaca in 2022?
|
17 |
+
- text: Which Category X Pack can we see the major share gain and which parameters
|
18 |
+
are driving the share gain in Cuernavaca?
|
19 |
+
pipeline_tag: text-classification
|
20 |
+
inference: true
|
21 |
+
base_model: intfloat/multilingual-e5-large
|
22 |
+
model-index:
|
23 |
+
- name: SetFit with intfloat/multilingual-e5-large
|
24 |
+
results:
|
25 |
+
- task:
|
26 |
+
type: text-classification
|
27 |
+
name: Text Classification
|
28 |
+
dataset:
|
29 |
+
name: Unknown
|
30 |
+
type: unknown
|
31 |
+
split: test
|
32 |
+
metrics:
|
33 |
+
- type: accuracy
|
34 |
+
value: 0.25
|
35 |
+
name: Accuracy
|
36 |
+
---
|
37 |
+
|
38 |
+
# SetFit with intfloat/multilingual-e5-large
|
39 |
+
|
40 |
+
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [intfloat/multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
|
41 |
+
|
42 |
+
The model has been trained using an efficient few-shot learning technique that involves:
|
43 |
+
|
44 |
+
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
|
45 |
+
2. Training a classification head with features from the fine-tuned Sentence Transformer.
|
46 |
+
|
47 |
+
## Model Details
|
48 |
+
|
49 |
+
### Model Description
|
50 |
+
- **Model Type:** SetFit
|
51 |
+
- **Sentence Transformer body:** [intfloat/multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large)
|
52 |
+
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
|
53 |
+
- **Maximum Sequence Length:** 512 tokens
|
54 |
+
- **Number of Classes:** 12 classes
|
55 |
+
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
|
56 |
+
<!-- - **Language:** Unknown -->
|
57 |
+
<!-- - **License:** Unknown -->
|
58 |
+
|
59 |
+
### Model Sources
|
60 |
+
|
61 |
+
- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
|
62 |
+
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
|
63 |
+
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
|
64 |
+
|
65 |
+
### Model Labels
|
66 |
+
| Label | Examples |
|
67 |
+
|:------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
68 |
+
| 6 | <ul><li>'Are there any major whitespace opportunity in terms of Categories x Pack Segments in Cuernavaca?'</li><li>'In Colas MS which packsegment is not dominated by KOF in TT HM Orizaba 2022? At what price point we can launch an offering'</li><li>'I want to launch a new pack type in csd for kof. Tell me what'</li></ul> |
|
69 |
+
| 2 | <ul><li>"Do any seasonal patterns exist in Jumex's share change in Orizaba?"</li><li>'What is the Market share for Resto in colas MS at each size groups in TT HM Orizaba in 2022'</li><li>'Which categories have seen the some of the highest Share losses for KOF in Cuernavaca in FY22-21?'</li></ul> |
|
70 |
+
| 0 | <ul><li>'Which packs have driven the shares for the competition in Colas in FY 21-22?'</li><li>'Apart from Jugos + Néctares, Which are the top contributing categoriesXconsumo to the share loss for Jumex in Orizaba in 2021?'</li><li>'which pack segment is contributing most to share change for Resto in Orizaba NCBs in 2022'</li></ul> |
|
71 |
+
| 10 | <ul><li>'Which pack segment shows opportunities to drive my market share in NCBS Colas SS?'</li><li>'What are my priority pack segments to gain share in NCB Colas SS?'</li><li>'What are my priority pack segments to gain share in AGUA Colas SS?'</li></ul> |
|
72 |
+
| 5 | <ul><li>'Where should I play in terms\xa0of flavor in Sabores SS?'</li><li>'I want to launch flavored water in onion flavor for kof.'</li><li>'What areas should I focus on to grow my market presence?'</li></ul> |
|
73 |
+
| 7 | <ul><li>'Is Fanta a premium brand? How premium are its offerings as compared to other brands in Sabores?'</li><li>"Is there potential for PPL correction in the packaging and pricing strategy of Tropicana's fruit juice offerings within the Juice category?"</li><li>'Is there an opportunity to premiumize any offerings for coca-cola?'</li></ul> |
|
74 |
+
| 9 | <ul><li>'Which industries to prioritize to gain share in AGUA in Cuernavaca?'</li><li>'What measures can be taken to maximize headroom in the AGUA market?'</li><li>'How much headroom do I have in CSDS'</li></ul> |
|
75 |
+
| 11 | <ul><li>'How can I gain share in NCBS?'</li><li>'How should KOF gain share in Colas MS in Cuernavaca? '</li><li>'How can I gain share in CSD Colas MS in Cuernavaca'</li></ul> |
|
76 |
+
| 8 | <ul><li>'Category wise market share'</li><li>'What is the ND, WD of KOF in colas'</li><li>'Tell me the top 10 SKUs in colas'</li></ul> |
|
77 |
+
| 3 | <ul><li>'What is the difference in offerings for KOF vs the key competitors in xx price bracket within CSD Colas in TT HM?'</li><li>'How should KOF gain share in <10 price bracket for NCB in TT HM'</li><li>'Which price points to play in?'</li></ul> |
|
78 |
+
| 1 | <ul><li>'what factors contributed to share change for agua?'</li><li>'Why is Resto losing share in Cuernavaca Colas SS RET Original?'</li><li>'What are the main factors contributing to the share gain of Jumex in Still Drinks MS in Orizaba for FY 2022?'</li></ul> |
|
79 |
+
| 4 | <ul><li>'How has the csd industry evolved in the last two years?'</li><li>'Tell me the categories to focus on, for driving growth in future'</li><li>'What is the change in industry mix for coca-cola in TT HM Orizaba in 2021 to 2022'</li></ul> |
|
80 |
+
|
81 |
+
## Evaluation
|
82 |
+
|
83 |
+
### Metrics
|
84 |
+
| Label | Accuracy |
|
85 |
+
|:--------|:---------|
|
86 |
+
| **all** | 0.25 |
|
87 |
+
|
88 |
+
## Uses
|
89 |
+
|
90 |
+
### Direct Use for Inference
|
91 |
+
|
92 |
+
First install the SetFit library:
|
93 |
+
|
94 |
+
```bash
|
95 |
+
pip install setfit
|
96 |
+
```
|
97 |
+
|
98 |
+
Then you can load this model and run inference.
|
99 |
+
|
100 |
+
```python
|
101 |
+
from setfit import SetFitModel
|
102 |
+
|
103 |
+
# Download from the 🤗 Hub
|
104 |
+
model = SetFitModel.from_pretrained("vgarg/fw_identification_model_e5_large_v5_14_02_24")
|
105 |
+
# Run inference
|
106 |
+
preds = model("Why is KOF losing share in Cuernavaca Colas MS RET Original?")
|
107 |
+
```
|
108 |
+
|
109 |
+
<!--
|
110 |
+
### Downstream Use
|
111 |
+
|
112 |
+
*List how someone could finetune this model on their own dataset.*
|
113 |
+
-->
|
114 |
+
|
115 |
+
<!--
|
116 |
+
### Out-of-Scope Use
|
117 |
+
|
118 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
119 |
+
-->
|
120 |
+
|
121 |
+
<!--
|
122 |
+
## Bias, Risks and Limitations
|
123 |
+
|
124 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
125 |
+
-->
|
126 |
+
|
127 |
+
<!--
|
128 |
+
### Recommendations
|
129 |
+
|
130 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
131 |
+
-->
|
132 |
+
|
133 |
+
## Training Details
|
134 |
+
|
135 |
+
### Training Set Metrics
|
136 |
+
| Training set | Min | Median | Max |
|
137 |
+
|:-------------|:----|:--------|:----|
|
138 |
+
| Word count | 4 | 13.5351 | 28 |
|
139 |
+
|
140 |
+
| Label | Training Sample Count |
|
141 |
+
|:------|:----------------------|
|
142 |
+
| 0 | 10 |
|
143 |
+
| 1 | 10 |
|
144 |
+
| 2 | 10 |
|
145 |
+
| 3 | 8 |
|
146 |
+
| 4 | 10 |
|
147 |
+
| 5 | 10 |
|
148 |
+
| 6 | 10 |
|
149 |
+
| 7 | 10 |
|
150 |
+
| 8 | 10 |
|
151 |
+
| 9 | 10 |
|
152 |
+
| 10 | 10 |
|
153 |
+
| 11 | 6 |
|
154 |
+
|
155 |
+
### Training Hyperparameters
|
156 |
+
- batch_size: (16, 16)
|
157 |
+
- num_epochs: (3, 3)
|
158 |
+
- max_steps: -1
|
159 |
+
- sampling_strategy: oversampling
|
160 |
+
- num_iterations: 20
|
161 |
+
- body_learning_rate: (2e-05, 2e-05)
|
162 |
+
- head_learning_rate: 2e-05
|
163 |
+
- loss: CosineSimilarityLoss
|
164 |
+
- distance_metric: cosine_distance
|
165 |
+
- margin: 0.25
|
166 |
+
- end_to_end: False
|
167 |
+
- use_amp: False
|
168 |
+
- warmup_proportion: 0.1
|
169 |
+
- seed: 42
|
170 |
+
- eval_max_steps: -1
|
171 |
+
- load_best_model_at_end: False
|
172 |
+
|
173 |
+
### Training Results
|
174 |
+
| Epoch | Step | Training Loss | Validation Loss |
|
175 |
+
|:------:|:----:|:-------------:|:---------------:|
|
176 |
+
| 0.0035 | 1 | 0.3481 | - |
|
177 |
+
| 0.1754 | 50 | 0.1442 | - |
|
178 |
+
| 0.3509 | 100 | 0.091 | - |
|
179 |
+
| 0.5263 | 150 | 0.0089 | - |
|
180 |
+
| 0.7018 | 200 | 0.0038 | - |
|
181 |
+
| 0.8772 | 250 | 0.0018 | - |
|
182 |
+
| 1.0526 | 300 | 0.001 | - |
|
183 |
+
| 1.2281 | 350 | 0.0012 | - |
|
184 |
+
| 1.4035 | 400 | 0.0007 | - |
|
185 |
+
| 1.5789 | 450 | 0.0007 | - |
|
186 |
+
| 1.7544 | 500 | 0.0004 | - |
|
187 |
+
| 1.9298 | 550 | 0.0005 | - |
|
188 |
+
| 2.1053 | 600 | 0.0006 | - |
|
189 |
+
| 2.2807 | 650 | 0.0005 | - |
|
190 |
+
| 2.4561 | 700 | 0.0006 | - |
|
191 |
+
| 2.6316 | 750 | 0.0004 | - |
|
192 |
+
| 2.8070 | 800 | 0.0004 | - |
|
193 |
+
| 2.9825 | 850 | 0.0004 | - |
|
194 |
+
|
195 |
+
### Framework Versions
|
196 |
+
- Python: 3.10.12
|
197 |
+
- SetFit: 1.0.3
|
198 |
+
- Sentence Transformers: 2.3.1
|
199 |
+
- Transformers: 4.35.2
|
200 |
+
- PyTorch: 2.1.0+cu121
|
201 |
+
- Datasets: 2.17.0
|
202 |
+
- Tokenizers: 0.15.1
|
203 |
+
|
204 |
+
## Citation
|
205 |
+
|
206 |
+
### BibTeX
|
207 |
+
```bibtex
|
208 |
+
@article{https://doi.org/10.48550/arxiv.2209.11055,
|
209 |
+
doi = {10.48550/ARXIV.2209.11055},
|
210 |
+
url = {https://arxiv.org/abs/2209.11055},
|
211 |
+
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
|
212 |
+
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
|
213 |
+
title = {Efficient Few-Shot Learning Without Prompts},
|
214 |
+
publisher = {arXiv},
|
215 |
+
year = {2022},
|
216 |
+
copyright = {Creative Commons Attribution 4.0 International}
|
217 |
+
}
|
218 |
+
```
|
219 |
+
|
220 |
+
<!--
|
221 |
+
## Glossary
|
222 |
+
|
223 |
+
*Clearly define terms in order to be accessible across audiences.*
|
224 |
+
-->
|
225 |
+
|
226 |
+
<!--
|
227 |
+
## Model Card Authors
|
228 |
+
|
229 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
230 |
+
-->
|
231 |
+
|
232 |
+
<!--
|
233 |
+
## Model Card Contact
|
234 |
+
|
235 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
236 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "intfloat/multilingual-e5-large",
|
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": 514,
|
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": "4.35.2",
|
25 |
+
"type_vocab_size": 1,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 250002
|
28 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "2.3.1",
|
4 |
+
"transformers": "4.35.2",
|
5 |
+
"pytorch": "2.1.0+cu121"
|
6 |
+
}
|
7 |
+
}
|
config_setfit.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"labels": null,
|
3 |
+
"normalize_embeddings": false
|
4 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8dc9b2039f94ba30877feb42d5dbafb3ba9ee2dfaba88e6f06f643089a77e3ab
|
3 |
+
size 2239607176
|
model_head.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bbeca4f713060257f4bde6335d369dfd9167f78f6edb446d09ef4245c71e6961
|
3 |
+
size 99335
|
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 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
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 |
+
}
|