miteshkotak7
commited on
Commit
•
cefc335
1
Parent(s):
132f0c6
Add SetFit model
Browse files- 1_Pooling/config.json +10 -0
- README.md +223 -0
- config.json +24 -0
- config_sentence_transformers.json +10 -0
- config_setfit.json +4 -0
- model.safetensors +3 -0
- model_head.pkl +3 -0
- modules.json +14 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +66 -0
- vocab.txt +0 -0
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 +1,223 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: sentence-transformers/paraphrase-mpnet-base-v2
|
3 |
+
datasets:
|
4 |
+
- clareandme/multiLabelClassification
|
5 |
+
library_name: setfit
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
pipeline_tag: text-classification
|
9 |
+
tags:
|
10 |
+
- setfit
|
11 |
+
- sentence-transformers
|
12 |
+
- text-classification
|
13 |
+
- generated_from_setfit_trainer
|
14 |
+
widget:
|
15 |
+
- text: The AI and user talk about how sleep problems are affecting the user's daily
|
16 |
+
life. The AI suggests improvements like sticking to a regular sleep schedule,
|
17 |
+
establishing a bedtime routine, and reducing screen time before bed. The user
|
18 |
+
acknowledges the challenge of implementing these changes but is willing to give
|
19 |
+
them a try for better sleep quality.
|
20 |
+
- text: The AI inquires about the user’s overall well-being and offers to talk about
|
21 |
+
managing work and study demands. The user reveals they’re feeling swamped by job
|
22 |
+
and exam pressures but find comfort in having a well-organized schedule.
|
23 |
+
- text: The AI and user talk about a recent falling out with a close friend who has
|
24 |
+
been giving them the cold shoulder. The user feels hurt and is uncertain about
|
25 |
+
the future of their friendship.
|
26 |
+
- text: The AI and user have a conversation about ways to manage and cope with the
|
27 |
+
loss of a loved partner.
|
28 |
+
- text: The AI engages the user in a conversation about their current challenges.
|
29 |
+
The user discloses that they’re feeling stressed and anxious due to financial
|
30 |
+
instability and rising debt.
|
31 |
+
inference: false
|
32 |
+
model-index:
|
33 |
+
- name: SetFit with sentence-transformers/paraphrase-mpnet-base-v2
|
34 |
+
results:
|
35 |
+
- task:
|
36 |
+
type: text-classification
|
37 |
+
name: Text Classification
|
38 |
+
dataset:
|
39 |
+
name: clareandme/multiLabelClassification
|
40 |
+
type: clareandme/multiLabelClassification
|
41 |
+
split: test
|
42 |
+
metrics:
|
43 |
+
- type: accuracy
|
44 |
+
value: 0.32142857142857145
|
45 |
+
name: Accuracy
|
46 |
+
---
|
47 |
+
|
48 |
+
# SetFit with sentence-transformers/paraphrase-mpnet-base-v2
|
49 |
+
|
50 |
+
This is a [SetFit](https://github.com/huggingface/setfit) model trained on the [clareandme/multiLabelClassification](https://huggingface.co/datasets/clareandme/multiLabelClassification) dataset that can be used for Text Classification. This SetFit model uses [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2) as the Sentence Transformer embedding model. A OneVsRestClassifier instance is used for classification.
|
51 |
+
|
52 |
+
The model has been trained using an efficient few-shot learning technique that involves:
|
53 |
+
|
54 |
+
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
|
55 |
+
2. Training a classification head with features from the fine-tuned Sentence Transformer.
|
56 |
+
|
57 |
+
## Model Details
|
58 |
+
|
59 |
+
### Model Description
|
60 |
+
- **Model Type:** SetFit
|
61 |
+
- **Sentence Transformer body:** [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2)
|
62 |
+
- **Classification head:** a OneVsRestClassifier instance
|
63 |
+
- **Maximum Sequence Length:** 512 tokens
|
64 |
+
<!-- - **Number of Classes:** Unknown -->
|
65 |
+
- **Training Dataset:** [clareandme/multiLabelClassification](https://huggingface.co/datasets/clareandme/multiLabelClassification)
|
66 |
+
<!-- - **Language:** Unknown -->
|
67 |
+
<!-- - **License:** Unknown -->
|
68 |
+
|
69 |
+
### Model Sources
|
70 |
+
|
71 |
+
- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
|
72 |
+
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
|
73 |
+
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
|
74 |
+
|
75 |
+
## Evaluation
|
76 |
+
|
77 |
+
### Metrics
|
78 |
+
| Label | Accuracy |
|
79 |
+
|:--------|:---------|
|
80 |
+
| **all** | 0.3214 |
|
81 |
+
|
82 |
+
## Uses
|
83 |
+
|
84 |
+
### Direct Use for Inference
|
85 |
+
|
86 |
+
First install the SetFit library:
|
87 |
+
|
88 |
+
```bash
|
89 |
+
pip install setfit
|
90 |
+
```
|
91 |
+
|
92 |
+
Then you can load this model and run inference.
|
93 |
+
|
94 |
+
```python
|
95 |
+
from setfit import SetFitModel
|
96 |
+
|
97 |
+
# Download from the 🤗 Hub
|
98 |
+
model = SetFitModel.from_pretrained("clareandme/multilabel-setfit-model-v2")
|
99 |
+
# Run inference
|
100 |
+
preds = model("The AI and user have a conversation about ways to manage and cope with the loss of a loved partner.")
|
101 |
+
```
|
102 |
+
|
103 |
+
<!--
|
104 |
+
### Downstream Use
|
105 |
+
|
106 |
+
*List how someone could finetune this model on their own dataset.*
|
107 |
+
-->
|
108 |
+
|
109 |
+
<!--
|
110 |
+
### Out-of-Scope Use
|
111 |
+
|
112 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
113 |
+
-->
|
114 |
+
|
115 |
+
<!--
|
116 |
+
## Bias, Risks and Limitations
|
117 |
+
|
118 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
119 |
+
-->
|
120 |
+
|
121 |
+
<!--
|
122 |
+
### Recommendations
|
123 |
+
|
124 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
125 |
+
-->
|
126 |
+
|
127 |
+
## Training Details
|
128 |
+
|
129 |
+
### Training Set Metrics
|
130 |
+
| Training set | Min | Median | Max |
|
131 |
+
|:-------------|:----|:-------|:----|
|
132 |
+
| Word count | 10 | 33.475 | 68 |
|
133 |
+
|
134 |
+
### Training Hyperparameters
|
135 |
+
- batch_size: (16, 16)
|
136 |
+
- num_epochs: (4, 4)
|
137 |
+
- max_steps: -1
|
138 |
+
- sampling_strategy: oversampling
|
139 |
+
- num_iterations: 20
|
140 |
+
- body_learning_rate: (2e-05, 1e-05)
|
141 |
+
- head_learning_rate: 0.01
|
142 |
+
- loss: CosineSimilarityLoss
|
143 |
+
- distance_metric: cosine_distance
|
144 |
+
- margin: 0.25
|
145 |
+
- end_to_end: False
|
146 |
+
- use_amp: False
|
147 |
+
- warmup_proportion: 0.1
|
148 |
+
- seed: 42
|
149 |
+
- eval_max_steps: -1
|
150 |
+
- load_best_model_at_end: True
|
151 |
+
|
152 |
+
### Training Results
|
153 |
+
| Epoch | Step | Training Loss | Validation Loss |
|
154 |
+
|:-------:|:-------:|:-------------:|:---------------:|
|
155 |
+
| 0.0033 | 1 | 0.1896 | - |
|
156 |
+
| 0.1667 | 50 | 0.2453 | - |
|
157 |
+
| 0.3333 | 100 | 0.1182 | - |
|
158 |
+
| 0.5 | 150 | 0.2458 | - |
|
159 |
+
| 0.6667 | 200 | 0.0401 | - |
|
160 |
+
| 0.8333 | 250 | 0.0763 | - |
|
161 |
+
| 1.0 | 300 | 0.0915 | 0.1302 |
|
162 |
+
| 1.1667 | 350 | 0.1105 | - |
|
163 |
+
| 1.3333 | 400 | 0.0715 | - |
|
164 |
+
| 1.5 | 450 | 0.126 | - |
|
165 |
+
| 1.6667 | 500 | 0.1074 | - |
|
166 |
+
| 1.8333 | 550 | 0.0781 | - |
|
167 |
+
| 2.0 | 600 | 0.0608 | 0.1102 |
|
168 |
+
| 2.1667 | 650 | 0.1246 | - |
|
169 |
+
| 2.3333 | 700 | 0.0791 | - |
|
170 |
+
| 2.5 | 750 | 0.0662 | - |
|
171 |
+
| 2.6667 | 800 | 0.0906 | - |
|
172 |
+
| 2.8333 | 850 | 0.0763 | - |
|
173 |
+
| **3.0** | **900** | **0.0656** | **0.1026** |
|
174 |
+
| 3.1667 | 950 | 0.0476 | - |
|
175 |
+
| 3.3333 | 1000 | 0.1086 | - |
|
176 |
+
| 3.5 | 1050 | 0.0903 | - |
|
177 |
+
| 3.6667 | 1100 | 0.0552 | - |
|
178 |
+
| 3.8333 | 1150 | 0.0335 | - |
|
179 |
+
| 4.0 | 1200 | 0.0689 | 0.1028 |
|
180 |
+
|
181 |
+
* The bold row denotes the saved checkpoint.
|
182 |
+
### Framework Versions
|
183 |
+
- Python: 3.10.12
|
184 |
+
- SetFit: 1.0.3
|
185 |
+
- Sentence Transformers: 3.0.1
|
186 |
+
- Transformers: 4.39.0
|
187 |
+
- PyTorch: 2.3.1+cu121
|
188 |
+
- Datasets: 2.21.0
|
189 |
+
- Tokenizers: 0.15.2
|
190 |
+
|
191 |
+
## Citation
|
192 |
+
|
193 |
+
### BibTeX
|
194 |
+
```bibtex
|
195 |
+
@article{https://doi.org/10.48550/arxiv.2209.11055,
|
196 |
+
doi = {10.48550/ARXIV.2209.11055},
|
197 |
+
url = {https://arxiv.org/abs/2209.11055},
|
198 |
+
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
|
199 |
+
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
|
200 |
+
title = {Efficient Few-Shot Learning Without Prompts},
|
201 |
+
publisher = {arXiv},
|
202 |
+
year = {2022},
|
203 |
+
copyright = {Creative Commons Attribution 4.0 International}
|
204 |
+
}
|
205 |
+
```
|
206 |
+
|
207 |
+
<!--
|
208 |
+
## Glossary
|
209 |
+
|
210 |
+
*Clearly define terms in order to be accessible across audiences.*
|
211 |
+
-->
|
212 |
+
|
213 |
+
<!--
|
214 |
+
## Model Card Authors
|
215 |
+
|
216 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
217 |
+
-->
|
218 |
+
|
219 |
+
<!--
|
220 |
+
## Model Card Contact
|
221 |
+
|
222 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
223 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "checkpoints/step_900",
|
3 |
+
"architectures": [
|
4 |
+
"MPNetModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-05,
|
15 |
+
"max_position_embeddings": 514,
|
16 |
+
"model_type": "mpnet",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 1,
|
20 |
+
"relative_attention_num_buckets": 32,
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.39.0",
|
23 |
+
"vocab_size": 30527
|
24 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "3.0.1",
|
4 |
+
"transformers": "4.39.0",
|
5 |
+
"pytorch": "2.3.1+cu121"
|
6 |
+
},
|
7 |
+
"prompts": {},
|
8 |
+
"default_prompt_name": null,
|
9 |
+
"similarity_fn_name": null
|
10 |
+
}
|
config_setfit.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"normalize_embeddings": false,
|
3 |
+
"labels": null
|
4 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3906cfcf9e7446a7e65694478ff6357b8743377516d3eeed3d2bb7ca7bcd17f9
|
3 |
+
size 437967672
|
model_head.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9557eb95056ce04ddb2ca759996d80474b37f5dc6b2c9e34f9cf007aaeb61363
|
3 |
+
size 175956
|
modules.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
]
|
sentence_bert_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"max_seq_length": 512,
|
3 |
+
"do_lower_case": false
|
4 |
+
}
|
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
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"104": {
|
28 |
+
"content": "[UNK]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"30526": {
|
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 |
+
"do_basic_tokenize": true,
|
48 |
+
"do_lower_case": true,
|
49 |
+
"eos_token": "</s>",
|
50 |
+
"mask_token": "<mask>",
|
51 |
+
"max_length": 512,
|
52 |
+
"model_max_length": 512,
|
53 |
+
"never_split": null,
|
54 |
+
"pad_to_multiple_of": null,
|
55 |
+
"pad_token": "<pad>",
|
56 |
+
"pad_token_type_id": 0,
|
57 |
+
"padding_side": "right",
|
58 |
+
"sep_token": "</s>",
|
59 |
+
"stride": 0,
|
60 |
+
"strip_accents": null,
|
61 |
+
"tokenize_chinese_chars": true,
|
62 |
+
"tokenizer_class": "MPNetTokenizer",
|
63 |
+
"truncation_side": "right",
|
64 |
+
"truncation_strategy": "longest_first",
|
65 |
+
"unk_token": "[UNK]"
|
66 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|