Updated Weights
Browse files- 1_Pooling/config.json +10 -0
- README.md +486 -0
- config.json +64 -0
- config_sentence_transformers.json +10 -0
- eval/Information-Retrieval_evaluation_test-eval_results.csv +11 -0
- model.safetensors +3 -0
- modules.json +14 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +125 -0
- tokenizer.json +0 -0
- tokenizer_config.json +939 -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 +1,486 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- sentence-transformers
|
| 4 |
+
- sentence-similarity
|
| 5 |
+
- feature-extraction
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
- dataset_size:3738
|
| 8 |
+
- loss:MultipleNegativesRankingLoss
|
| 9 |
+
- loss:CosineSimilarityLoss
|
| 10 |
+
base_model: jinaai/jina-embedding-b-en-v1
|
| 11 |
+
widget:
|
| 12 |
+
- source_sentence: What's the status of my portfolio?
|
| 13 |
+
sentences:
|
| 14 |
+
- Show my funds portfolio
|
| 15 |
+
- How risky is my portfolio currently?
|
| 16 |
+
- How is my portfolio performing
|
| 17 |
+
- source_sentence: How does my portfolio risk compare to the market?
|
| 18 |
+
sentences:
|
| 19 |
+
- Switch my stock portfolio with mutual funds
|
| 20 |
+
- View my ETFs
|
| 21 |
+
- Is my portfolio risk higher or lower than the market?
|
| 22 |
+
- source_sentence: Can you tell me if I have stocks?
|
| 23 |
+
sentences:
|
| 24 |
+
- Do I have any stocks in my portfolio?
|
| 25 |
+
- Show my dividend yielding investments.
|
| 26 |
+
- Is my portfolio risk higher or lower than the market?
|
| 27 |
+
- source_sentence: Can you help me with switching my stocks to mutual funds?
|
| 28 |
+
sentences:
|
| 29 |
+
- Is my portfolio risk higher or lower than the market?
|
| 30 |
+
- Switch my stock portfolio with mutual funds
|
| 31 |
+
- Show my stock portfolio score
|
| 32 |
+
- source_sentence: Are there any costly funds that I own?
|
| 33 |
+
sentences:
|
| 34 |
+
- What is my exposure to X
|
| 35 |
+
- Can I save more on fees in my portfolio?
|
| 36 |
+
- Do I hold any costly funds ?
|
| 37 |
+
pipeline_tag: sentence-similarity
|
| 38 |
+
library_name: sentence-transformers
|
| 39 |
+
metrics:
|
| 40 |
+
- cosine_accuracy@1
|
| 41 |
+
- cosine_accuracy@3
|
| 42 |
+
- cosine_accuracy@5
|
| 43 |
+
- cosine_accuracy@10
|
| 44 |
+
- cosine_precision@1
|
| 45 |
+
- cosine_precision@3
|
| 46 |
+
- cosine_precision@5
|
| 47 |
+
- cosine_precision@10
|
| 48 |
+
- cosine_recall@1
|
| 49 |
+
- cosine_recall@3
|
| 50 |
+
- cosine_recall@5
|
| 51 |
+
- cosine_recall@10
|
| 52 |
+
- cosine_ndcg@10
|
| 53 |
+
- cosine_mrr@10
|
| 54 |
+
- cosine_map@100
|
| 55 |
+
model-index:
|
| 56 |
+
- name: SentenceTransformer based on jinaai/jina-embedding-b-en-v1
|
| 57 |
+
results:
|
| 58 |
+
- task:
|
| 59 |
+
type: information-retrieval
|
| 60 |
+
name: Information Retrieval
|
| 61 |
+
dataset:
|
| 62 |
+
name: test eval
|
| 63 |
+
type: test-eval
|
| 64 |
+
metrics:
|
| 65 |
+
- type: cosine_accuracy@1
|
| 66 |
+
value: 0.8693333333333333
|
| 67 |
+
name: Cosine Accuracy@1
|
| 68 |
+
- type: cosine_accuracy@3
|
| 69 |
+
value: 0.992
|
| 70 |
+
name: Cosine Accuracy@3
|
| 71 |
+
- type: cosine_accuracy@5
|
| 72 |
+
value: 1.0
|
| 73 |
+
name: Cosine Accuracy@5
|
| 74 |
+
- type: cosine_accuracy@10
|
| 75 |
+
value: 1.0
|
| 76 |
+
name: Cosine Accuracy@10
|
| 77 |
+
- type: cosine_precision@1
|
| 78 |
+
value: 0.8693333333333333
|
| 79 |
+
name: Cosine Precision@1
|
| 80 |
+
- type: cosine_precision@3
|
| 81 |
+
value: 0.3306666666666667
|
| 82 |
+
name: Cosine Precision@3
|
| 83 |
+
- type: cosine_precision@5
|
| 84 |
+
value: 0.19999999999999996
|
| 85 |
+
name: Cosine Precision@5
|
| 86 |
+
- type: cosine_precision@10
|
| 87 |
+
value: 0.09999999999999998
|
| 88 |
+
name: Cosine Precision@10
|
| 89 |
+
- type: cosine_recall@1
|
| 90 |
+
value: 0.8693333333333333
|
| 91 |
+
name: Cosine Recall@1
|
| 92 |
+
- type: cosine_recall@3
|
| 93 |
+
value: 0.992
|
| 94 |
+
name: Cosine Recall@3
|
| 95 |
+
- type: cosine_recall@5
|
| 96 |
+
value: 1.0
|
| 97 |
+
name: Cosine Recall@5
|
| 98 |
+
- type: cosine_recall@10
|
| 99 |
+
value: 1.0
|
| 100 |
+
name: Cosine Recall@10
|
| 101 |
+
- type: cosine_ndcg@10
|
| 102 |
+
value: 0.9465644721385433
|
| 103 |
+
name: Cosine Ndcg@10
|
| 104 |
+
- type: cosine_mrr@10
|
| 105 |
+
value: 0.9280888888888886
|
| 106 |
+
name: Cosine Mrr@10
|
| 107 |
+
- type: cosine_map@100
|
| 108 |
+
value: 0.9280888888888889
|
| 109 |
+
name: Cosine Map@100
|
| 110 |
+
---
|
| 111 |
+
|
| 112 |
+
# SentenceTransformer based on jinaai/jina-embedding-b-en-v1
|
| 113 |
+
|
| 114 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [jinaai/jina-embedding-b-en-v1](https://huggingface.co/jinaai/jina-embedding-b-en-v1). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
|
| 115 |
+
|
| 116 |
+
## Model Details
|
| 117 |
+
|
| 118 |
+
### Model Description
|
| 119 |
+
- **Model Type:** Sentence Transformer
|
| 120 |
+
- **Base model:** [jinaai/jina-embedding-b-en-v1](https://huggingface.co/jinaai/jina-embedding-b-en-v1) <!-- at revision 32aa658e5ceb90793454d22a57d8e3a14e699516 -->
|
| 121 |
+
- **Maximum Sequence Length:** 512 tokens
|
| 122 |
+
- **Output Dimensionality:** 768 dimensions
|
| 123 |
+
- **Similarity Function:** Cosine Similarity
|
| 124 |
+
<!-- - **Training Dataset:** Unknown -->
|
| 125 |
+
<!-- - **Language:** Unknown -->
|
| 126 |
+
<!-- - **License:** Unknown -->
|
| 127 |
+
|
| 128 |
+
### Model Sources
|
| 129 |
+
|
| 130 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
| 131 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
| 132 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
| 133 |
+
|
| 134 |
+
### Full Model Architecture
|
| 135 |
+
|
| 136 |
+
```
|
| 137 |
+
SentenceTransformer(
|
| 138 |
+
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: T5EncoderModel
|
| 139 |
+
(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})
|
| 140 |
+
)
|
| 141 |
+
```
|
| 142 |
+
|
| 143 |
+
## Usage
|
| 144 |
+
|
| 145 |
+
### Direct Usage (Sentence Transformers)
|
| 146 |
+
|
| 147 |
+
First install the Sentence Transformers library:
|
| 148 |
+
|
| 149 |
+
```bash
|
| 150 |
+
pip install -U sentence-transformers
|
| 151 |
+
```
|
| 152 |
+
|
| 153 |
+
Then you can load this model and run inference.
|
| 154 |
+
```python
|
| 155 |
+
from sentence_transformers import SentenceTransformer
|
| 156 |
+
|
| 157 |
+
# Download from the 🤗 Hub
|
| 158 |
+
model = SentenceTransformer("sentence_transformers_model_id")
|
| 159 |
+
# Run inference
|
| 160 |
+
sentences = [
|
| 161 |
+
'Are there any costly funds that I own?',
|
| 162 |
+
'Do I hold any costly funds ?',
|
| 163 |
+
'What is my exposure to X',
|
| 164 |
+
]
|
| 165 |
+
embeddings = model.encode(sentences)
|
| 166 |
+
print(embeddings.shape)
|
| 167 |
+
# [3, 768]
|
| 168 |
+
|
| 169 |
+
# Get the similarity scores for the embeddings
|
| 170 |
+
similarities = model.similarity(embeddings, embeddings)
|
| 171 |
+
print(similarities.shape)
|
| 172 |
+
# [3, 3]
|
| 173 |
+
```
|
| 174 |
+
|
| 175 |
+
<!--
|
| 176 |
+
### Direct Usage (Transformers)
|
| 177 |
+
|
| 178 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
| 179 |
+
|
| 180 |
+
</details>
|
| 181 |
+
-->
|
| 182 |
+
|
| 183 |
+
<!--
|
| 184 |
+
### Downstream Usage (Sentence Transformers)
|
| 185 |
+
|
| 186 |
+
You can finetune this model on your own dataset.
|
| 187 |
+
|
| 188 |
+
<details><summary>Click to expand</summary>
|
| 189 |
+
|
| 190 |
+
</details>
|
| 191 |
+
-->
|
| 192 |
+
|
| 193 |
+
<!--
|
| 194 |
+
### Out-of-Scope Use
|
| 195 |
+
|
| 196 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
| 197 |
+
-->
|
| 198 |
+
|
| 199 |
+
## Evaluation
|
| 200 |
+
|
| 201 |
+
### Metrics
|
| 202 |
+
|
| 203 |
+
#### Information Retrieval
|
| 204 |
+
|
| 205 |
+
* Dataset: `test-eval`
|
| 206 |
+
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
|
| 207 |
+
|
| 208 |
+
| Metric | Value |
|
| 209 |
+
|:--------------------|:-----------|
|
| 210 |
+
| cosine_accuracy@1 | 0.8693 |
|
| 211 |
+
| cosine_accuracy@3 | 0.992 |
|
| 212 |
+
| cosine_accuracy@5 | 1.0 |
|
| 213 |
+
| cosine_accuracy@10 | 1.0 |
|
| 214 |
+
| cosine_precision@1 | 0.8693 |
|
| 215 |
+
| cosine_precision@3 | 0.3307 |
|
| 216 |
+
| cosine_precision@5 | 0.2 |
|
| 217 |
+
| cosine_precision@10 | 0.1 |
|
| 218 |
+
| cosine_recall@1 | 0.8693 |
|
| 219 |
+
| cosine_recall@3 | 0.992 |
|
| 220 |
+
| cosine_recall@5 | 1.0 |
|
| 221 |
+
| cosine_recall@10 | 1.0 |
|
| 222 |
+
| **cosine_ndcg@10** | **0.9466** |
|
| 223 |
+
| cosine_mrr@10 | 0.9281 |
|
| 224 |
+
| cosine_map@100 | 0.9281 |
|
| 225 |
+
|
| 226 |
+
<!--
|
| 227 |
+
## Bias, Risks and Limitations
|
| 228 |
+
|
| 229 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
| 230 |
+
-->
|
| 231 |
+
|
| 232 |
+
<!--
|
| 233 |
+
### Recommendations
|
| 234 |
+
|
| 235 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
| 236 |
+
-->
|
| 237 |
+
|
| 238 |
+
## Training Details
|
| 239 |
+
|
| 240 |
+
### Training Datasets
|
| 241 |
+
|
| 242 |
+
#### Unnamed Dataset
|
| 243 |
+
|
| 244 |
+
* Size: 1,869 training samples
|
| 245 |
+
* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code>
|
| 246 |
+
* Approximate statistics based on the first 1000 samples:
|
| 247 |
+
| | sentence_0 | sentence_1 | label |
|
| 248 |
+
|:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:--------------------------------------------------------------|
|
| 249 |
+
| type | string | string | float |
|
| 250 |
+
| details | <ul><li>min: 4 tokens</li><li>mean: 11.3 tokens</li><li>max: 26 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 9.93 tokens</li><li>max: 33 tokens</li></ul> | <ul><li>min: 1.0</li><li>mean: 1.0</li><li>max: 1.0</li></ul> |
|
| 251 |
+
* Samples:
|
| 252 |
+
| sentence_0 | sentence_1 | label |
|
| 253 |
+
|:-----------------------------------------------------------------------------|:--------------------------------------------------------------------------|:-----------------|
|
| 254 |
+
| <code>Can you help me with my red flags?</code> | <code>How to deal with my red flags?</code> | <code>1.0</code> |
|
| 255 |
+
| <code>Check if Axis Bluechip Fund is in my portfolio, please.</code> | <code>Do I have Axis Bluechip Fund in my portfolio?</code> | <code>1.0</code> |
|
| 256 |
+
| <code>How much can I expect my portfolio to grow in the next 5 years?</code> | <code>What is my portfolio's growth potential in the next 5 years?</code> | <code>1.0</code> |
|
| 257 |
+
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
|
| 258 |
+
```json
|
| 259 |
+
{
|
| 260 |
+
"scale": 20.0,
|
| 261 |
+
"similarity_fct": "cos_sim"
|
| 262 |
+
}
|
| 263 |
+
```
|
| 264 |
+
|
| 265 |
+
#### Unnamed Dataset
|
| 266 |
+
|
| 267 |
+
* Size: 1,869 training samples
|
| 268 |
+
* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code>
|
| 269 |
+
* Approximate statistics based on the first 1000 samples:
|
| 270 |
+
| | sentence_0 | sentence_1 | label |
|
| 271 |
+
|:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:--------------------------------------------------------------|
|
| 272 |
+
| type | string | string | float |
|
| 273 |
+
| details | <ul><li>min: 4 tokens</li><li>mean: 11.32 tokens</li><li>max: 26 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 9.89 tokens</li><li>max: 33 tokens</li></ul> | <ul><li>min: 1.0</li><li>mean: 1.0</li><li>max: 1.0</li></ul> |
|
| 274 |
+
* Samples:
|
| 275 |
+
| sentence_0 | sentence_1 | label |
|
| 276 |
+
|:------------------------------------------------------------------|:---------------------------------------------------------------|:-----------------|
|
| 277 |
+
| <code>Do I need to adjust my portfolio for better profits?</code> | <code>Should I change my portfolio to make more profit?</code> | <code>1.0</code> |
|
| 278 |
+
| <code>Which stocks in my collection are the most volatile?</code> | <code>Which of my stocks are most volatile?</code> | <code>1.0</code> |
|
| 279 |
+
| <code>Display my report card</code> | <code>View my report card</code> | <code>1.0</code> |
|
| 280 |
+
* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
|
| 281 |
+
```json
|
| 282 |
+
{
|
| 283 |
+
"loss_fct": "torch.nn.modules.loss.MSELoss"
|
| 284 |
+
}
|
| 285 |
+
```
|
| 286 |
+
|
| 287 |
+
### Training Hyperparameters
|
| 288 |
+
#### Non-Default Hyperparameters
|
| 289 |
+
|
| 290 |
+
- `eval_strategy`: steps
|
| 291 |
+
- `per_device_train_batch_size`: 32
|
| 292 |
+
- `per_device_eval_batch_size`: 32
|
| 293 |
+
- `num_train_epochs`: 10
|
| 294 |
+
- `multi_dataset_batch_sampler`: round_robin
|
| 295 |
+
|
| 296 |
+
#### All Hyperparameters
|
| 297 |
+
<details><summary>Click to expand</summary>
|
| 298 |
+
|
| 299 |
+
- `overwrite_output_dir`: False
|
| 300 |
+
- `do_predict`: False
|
| 301 |
+
- `eval_strategy`: steps
|
| 302 |
+
- `prediction_loss_only`: True
|
| 303 |
+
- `per_device_train_batch_size`: 32
|
| 304 |
+
- `per_device_eval_batch_size`: 32
|
| 305 |
+
- `per_gpu_train_batch_size`: None
|
| 306 |
+
- `per_gpu_eval_batch_size`: None
|
| 307 |
+
- `gradient_accumulation_steps`: 1
|
| 308 |
+
- `eval_accumulation_steps`: None
|
| 309 |
+
- `torch_empty_cache_steps`: None
|
| 310 |
+
- `learning_rate`: 5e-05
|
| 311 |
+
- `weight_decay`: 0.0
|
| 312 |
+
- `adam_beta1`: 0.9
|
| 313 |
+
- `adam_beta2`: 0.999
|
| 314 |
+
- `adam_epsilon`: 1e-08
|
| 315 |
+
- `max_grad_norm`: 1
|
| 316 |
+
- `num_train_epochs`: 10
|
| 317 |
+
- `max_steps`: -1
|
| 318 |
+
- `lr_scheduler_type`: linear
|
| 319 |
+
- `lr_scheduler_kwargs`: {}
|
| 320 |
+
- `warmup_ratio`: 0.0
|
| 321 |
+
- `warmup_steps`: 0
|
| 322 |
+
- `log_level`: passive
|
| 323 |
+
- `log_level_replica`: warning
|
| 324 |
+
- `log_on_each_node`: True
|
| 325 |
+
- `logging_nan_inf_filter`: True
|
| 326 |
+
- `save_safetensors`: True
|
| 327 |
+
- `save_on_each_node`: False
|
| 328 |
+
- `save_only_model`: False
|
| 329 |
+
- `restore_callback_states_from_checkpoint`: False
|
| 330 |
+
- `no_cuda`: False
|
| 331 |
+
- `use_cpu`: False
|
| 332 |
+
- `use_mps_device`: False
|
| 333 |
+
- `seed`: 42
|
| 334 |
+
- `data_seed`: None
|
| 335 |
+
- `jit_mode_eval`: False
|
| 336 |
+
- `use_ipex`: False
|
| 337 |
+
- `bf16`: False
|
| 338 |
+
- `fp16`: False
|
| 339 |
+
- `fp16_opt_level`: O1
|
| 340 |
+
- `half_precision_backend`: auto
|
| 341 |
+
- `bf16_full_eval`: False
|
| 342 |
+
- `fp16_full_eval`: False
|
| 343 |
+
- `tf32`: None
|
| 344 |
+
- `local_rank`: 0
|
| 345 |
+
- `ddp_backend`: None
|
| 346 |
+
- `tpu_num_cores`: None
|
| 347 |
+
- `tpu_metrics_debug`: False
|
| 348 |
+
- `debug`: []
|
| 349 |
+
- `dataloader_drop_last`: False
|
| 350 |
+
- `dataloader_num_workers`: 0
|
| 351 |
+
- `dataloader_prefetch_factor`: None
|
| 352 |
+
- `past_index`: -1
|
| 353 |
+
- `disable_tqdm`: False
|
| 354 |
+
- `remove_unused_columns`: True
|
| 355 |
+
- `label_names`: None
|
| 356 |
+
- `load_best_model_at_end`: False
|
| 357 |
+
- `ignore_data_skip`: False
|
| 358 |
+
- `fsdp`: []
|
| 359 |
+
- `fsdp_min_num_params`: 0
|
| 360 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
| 361 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
| 362 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
| 363 |
+
- `deepspeed`: None
|
| 364 |
+
- `label_smoothing_factor`: 0.0
|
| 365 |
+
- `optim`: adamw_torch
|
| 366 |
+
- `optim_args`: None
|
| 367 |
+
- `adafactor`: False
|
| 368 |
+
- `group_by_length`: False
|
| 369 |
+
- `length_column_name`: length
|
| 370 |
+
- `ddp_find_unused_parameters`: None
|
| 371 |
+
- `ddp_bucket_cap_mb`: None
|
| 372 |
+
- `ddp_broadcast_buffers`: False
|
| 373 |
+
- `dataloader_pin_memory`: True
|
| 374 |
+
- `dataloader_persistent_workers`: False
|
| 375 |
+
- `skip_memory_metrics`: True
|
| 376 |
+
- `use_legacy_prediction_loop`: False
|
| 377 |
+
- `push_to_hub`: False
|
| 378 |
+
- `resume_from_checkpoint`: None
|
| 379 |
+
- `hub_model_id`: None
|
| 380 |
+
- `hub_strategy`: every_save
|
| 381 |
+
- `hub_private_repo`: None
|
| 382 |
+
- `hub_always_push`: False
|
| 383 |
+
- `gradient_checkpointing`: False
|
| 384 |
+
- `gradient_checkpointing_kwargs`: None
|
| 385 |
+
- `include_inputs_for_metrics`: False
|
| 386 |
+
- `include_for_metrics`: []
|
| 387 |
+
- `eval_do_concat_batches`: True
|
| 388 |
+
- `fp16_backend`: auto
|
| 389 |
+
- `push_to_hub_model_id`: None
|
| 390 |
+
- `push_to_hub_organization`: None
|
| 391 |
+
- `mp_parameters`:
|
| 392 |
+
- `auto_find_batch_size`: False
|
| 393 |
+
- `full_determinism`: False
|
| 394 |
+
- `torchdynamo`: None
|
| 395 |
+
- `ray_scope`: last
|
| 396 |
+
- `ddp_timeout`: 1800
|
| 397 |
+
- `torch_compile`: False
|
| 398 |
+
- `torch_compile_backend`: None
|
| 399 |
+
- `torch_compile_mode`: None
|
| 400 |
+
- `dispatch_batches`: None
|
| 401 |
+
- `split_batches`: None
|
| 402 |
+
- `include_tokens_per_second`: False
|
| 403 |
+
- `include_num_input_tokens_seen`: False
|
| 404 |
+
- `neftune_noise_alpha`: None
|
| 405 |
+
- `optim_target_modules`: None
|
| 406 |
+
- `batch_eval_metrics`: False
|
| 407 |
+
- `eval_on_start`: False
|
| 408 |
+
- `use_liger_kernel`: False
|
| 409 |
+
- `eval_use_gather_object`: False
|
| 410 |
+
- `average_tokens_across_devices`: False
|
| 411 |
+
- `prompts`: None
|
| 412 |
+
- `batch_sampler`: batch_sampler
|
| 413 |
+
- `multi_dataset_batch_sampler`: round_robin
|
| 414 |
+
|
| 415 |
+
</details>
|
| 416 |
+
|
| 417 |
+
### Training Logs
|
| 418 |
+
| Epoch | Step | Training Loss | test-eval_cosine_ndcg@10 |
|
| 419 |
+
|:------:|:----:|:-------------:|:------------------------:|
|
| 420 |
+
| 1.0 | 118 | - | 0.9029 |
|
| 421 |
+
| 2.0 | 236 | - | 0.9145 |
|
| 422 |
+
| 3.0 | 354 | - | 0.9276 |
|
| 423 |
+
| 4.0 | 472 | - | 0.9338 |
|
| 424 |
+
| 4.2373 | 500 | 0.2022 | 0.9329 |
|
| 425 |
+
| 5.0 | 590 | - | 0.9393 |
|
| 426 |
+
| 6.0 | 708 | - | 0.9385 |
|
| 427 |
+
| 7.0 | 826 | - | 0.9400 |
|
| 428 |
+
| 8.0 | 944 | - | 0.9449 |
|
| 429 |
+
| 8.4746 | 1000 | 0.1354 | 0.9466 |
|
| 430 |
+
|
| 431 |
+
|
| 432 |
+
### Framework Versions
|
| 433 |
+
- Python: 3.12.5
|
| 434 |
+
- Sentence Transformers: 3.4.1
|
| 435 |
+
- Transformers: 4.49.0
|
| 436 |
+
- PyTorch: 2.6.0
|
| 437 |
+
- Accelerate: 1.5.2
|
| 438 |
+
- Datasets: 3.4.1
|
| 439 |
+
- Tokenizers: 0.21.1
|
| 440 |
+
|
| 441 |
+
## Citation
|
| 442 |
+
|
| 443 |
+
### BibTeX
|
| 444 |
+
|
| 445 |
+
#### Sentence Transformers
|
| 446 |
+
```bibtex
|
| 447 |
+
@inproceedings{reimers-2019-sentence-bert,
|
| 448 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
| 449 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
| 450 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
| 451 |
+
month = "11",
|
| 452 |
+
year = "2019",
|
| 453 |
+
publisher = "Association for Computational Linguistics",
|
| 454 |
+
url = "https://arxiv.org/abs/1908.10084",
|
| 455 |
+
}
|
| 456 |
+
```
|
| 457 |
+
|
| 458 |
+
#### MultipleNegativesRankingLoss
|
| 459 |
+
```bibtex
|
| 460 |
+
@misc{henderson2017efficient,
|
| 461 |
+
title={Efficient Natural Language Response Suggestion for Smart Reply},
|
| 462 |
+
author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
|
| 463 |
+
year={2017},
|
| 464 |
+
eprint={1705.00652},
|
| 465 |
+
archivePrefix={arXiv},
|
| 466 |
+
primaryClass={cs.CL}
|
| 467 |
+
}
|
| 468 |
+
```
|
| 469 |
+
|
| 470 |
+
<!--
|
| 471 |
+
## Glossary
|
| 472 |
+
|
| 473 |
+
*Clearly define terms in order to be accessible across audiences.*
|
| 474 |
+
-->
|
| 475 |
+
|
| 476 |
+
<!--
|
| 477 |
+
## Model Card Authors
|
| 478 |
+
|
| 479 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
| 480 |
+
-->
|
| 481 |
+
|
| 482 |
+
<!--
|
| 483 |
+
## Model Card Contact
|
| 484 |
+
|
| 485 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
| 486 |
+
-->
|
config.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "jinaai/jina-embedding-b-en-v1",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5EncoderModel"
|
| 5 |
+
],
|
| 6 |
+
"auto_map": {
|
| 7 |
+
"AutoModel": "jinaai/jina-embedding-b-en-v1--modeling_t5.T5EncoderModel"
|
| 8 |
+
},
|
| 9 |
+
"classifier_dropout": 0.0,
|
| 10 |
+
"d_ff": 3072,
|
| 11 |
+
"d_kv": 64,
|
| 12 |
+
"d_model": 768,
|
| 13 |
+
"decoder_start_token_id": 0,
|
| 14 |
+
"dense_act_fn": "relu",
|
| 15 |
+
"dropout_rate": 0.1,
|
| 16 |
+
"eos_token_id": 1,
|
| 17 |
+
"feed_forward_proj": "relu",
|
| 18 |
+
"initializer_factor": 1.0,
|
| 19 |
+
"is_encoder_decoder": true,
|
| 20 |
+
"is_gated_act": false,
|
| 21 |
+
"layer_norm_epsilon": 1e-06,
|
| 22 |
+
"model_type": "t5",
|
| 23 |
+
"n_positions": 512,
|
| 24 |
+
"num_decoder_layers": 12,
|
| 25 |
+
"num_heads": 12,
|
| 26 |
+
"num_layers": 12,
|
| 27 |
+
"output_past": true,
|
| 28 |
+
"pad_token_id": 0,
|
| 29 |
+
"relative_attention_max_distance": 128,
|
| 30 |
+
"relative_attention_num_buckets": 32,
|
| 31 |
+
"task_specific_params": {
|
| 32 |
+
"summarization": {
|
| 33 |
+
"early_stopping": true,
|
| 34 |
+
"length_penalty": 2.0,
|
| 35 |
+
"max_length": 200,
|
| 36 |
+
"min_length": 30,
|
| 37 |
+
"no_repeat_ngram_size": 3,
|
| 38 |
+
"num_beams": 4,
|
| 39 |
+
"prefix": "summarize: "
|
| 40 |
+
},
|
| 41 |
+
"translation_en_to_de": {
|
| 42 |
+
"early_stopping": true,
|
| 43 |
+
"max_length": 300,
|
| 44 |
+
"num_beams": 4,
|
| 45 |
+
"prefix": "translate English to German: "
|
| 46 |
+
},
|
| 47 |
+
"translation_en_to_fr": {
|
| 48 |
+
"early_stopping": true,
|
| 49 |
+
"max_length": 300,
|
| 50 |
+
"num_beams": 4,
|
| 51 |
+
"prefix": "translate English to French: "
|
| 52 |
+
},
|
| 53 |
+
"translation_en_to_ro": {
|
| 54 |
+
"early_stopping": true,
|
| 55 |
+
"max_length": 300,
|
| 56 |
+
"num_beams": 4,
|
| 57 |
+
"prefix": "translate English to Romanian: "
|
| 58 |
+
}
|
| 59 |
+
},
|
| 60 |
+
"torch_dtype": "float32",
|
| 61 |
+
"transformers_version": "4.49.0",
|
| 62 |
+
"use_cache": true,
|
| 63 |
+
"vocab_size": 32128
|
| 64 |
+
}
|
config_sentence_transformers.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"__version__": {
|
| 3 |
+
"sentence_transformers": "3.4.1",
|
| 4 |
+
"transformers": "4.49.0",
|
| 5 |
+
"pytorch": "2.6.0"
|
| 6 |
+
},
|
| 7 |
+
"prompts": {},
|
| 8 |
+
"default_prompt_name": null,
|
| 9 |
+
"similarity_fn_name": "cosine"
|
| 10 |
+
}
|
eval/Information-Retrieval_evaluation_test-eval_results.csv
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accuracy@10,cosine-Precision@1,cosine-Recall@1,cosine-Precision@3,cosine-Recall@3,cosine-Precision@5,cosine-Recall@5,cosine-Precision@10,cosine-Recall@10,cosine-MRR@10,cosine-NDCG@10,cosine-MAP@100
|
| 2 |
+
1.0,118,0.8026666666666666,0.9413333333333334,0.9653333333333334,0.9866666666666667,0.8026666666666666,0.8026666666666666,0.31377777777777777,0.9413333333333334,0.1930666666666666,0.9653333333333334,0.09866666666666667,0.9866666666666667,0.8752105820105817,0.9029460996885681,0.8759875769836554
|
| 3 |
+
2.0,236,0.8133333333333334,0.9573333333333334,0.9786666666666667,0.9973333333333333,0.8133333333333334,0.8133333333333334,0.3191111111111111,0.9573333333333334,0.19573333333333331,0.9786666666666667,0.09973333333333331,0.9973333333333333,0.8868550264550263,0.9144769859990948,0.8869383597883598
|
| 4 |
+
3.0,354,0.8373333333333334,0.9706666666666667,0.9866666666666667,0.9973333333333333,0.8373333333333334,0.8373333333333334,0.3235555555555556,0.9706666666666667,0.19733333333333333,0.9866666666666667,0.09973333333333331,0.9973333333333333,0.9040994708994708,0.9275692902070236,0.904304599104599
|
| 5 |
+
4.0,472,0.8506666666666667,0.9706666666666667,0.9893333333333333,0.9973333333333333,0.8506666666666667,0.8506666666666667,0.3235555555555556,0.9706666666666667,0.19786666666666664,0.9893333333333333,0.09973333333333331,0.9973333333333333,0.9123216931216931,0.9337998768009405,0.9125268213268213
|
| 6 |
+
5.0,590,0.8586666666666667,0.9786666666666667,0.992,1.0,0.8586666666666667,0.8586666666666667,0.32622222222222225,0.9786666666666667,0.19839999999999997,0.992,0.09999999999999998,1.0,0.9187439153439153,0.9392774256614527,0.9187439153439153
|
| 7 |
+
6.0,708,0.856,0.9786666666666667,0.9946666666666667,1.0,0.856,0.856,0.32622222222222225,0.9786666666666667,0.19893333333333332,0.9946666666666667,0.09999999999999998,1.0,0.9175809523809523,0.9384516990339171,0.9175809523809524
|
| 8 |
+
7.0,826,0.8586666666666667,0.9813333333333333,0.9946666666666667,1.0,0.8586666666666667,0.8586666666666667,0.3271111111111112,0.9813333333333333,0.19893333333333332,0.9946666666666667,0.09999999999999998,1.0,0.919511111111111,0.9399776554439405,0.9195111111111111
|
| 9 |
+
8.0,944,0.8693333333333333,0.9893333333333333,1.0,1.0,0.8693333333333333,0.8693333333333333,0.32977777777777784,0.9893333333333333,0.19999999999999996,1.0,0.09999999999999998,1.0,0.9259555555555553,0.9448661622530734,0.9259555555555556
|
| 10 |
+
9.0,1062,0.8693333333333333,0.992,1.0,1.0,0.8693333333333333,0.8693333333333333,0.3306666666666667,0.992,0.19999999999999996,1.0,0.09999999999999998,1.0,0.9280888888888886,0.9465644721385433,0.9280888888888889
|
| 11 |
+
10.0,1180,0.8693333333333333,0.992,1.0,1.0,0.8693333333333333,0.8693333333333333,0.3306666666666667,0.992,0.19999999999999996,1.0,0.09999999999999998,1.0,0.9280888888888886,0.9465644721385433,0.9280888888888889
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3454030b568244fd1c4602d3045aa17123af6abd979440a2cb9ed92b3ec59be2
|
| 3 |
+
size 438525864
|
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 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>"
|
| 103 |
+
],
|
| 104 |
+
"eos_token": {
|
| 105 |
+
"content": "</s>",
|
| 106 |
+
"lstrip": false,
|
| 107 |
+
"normalized": false,
|
| 108 |
+
"rstrip": false,
|
| 109 |
+
"single_word": false
|
| 110 |
+
},
|
| 111 |
+
"pad_token": {
|
| 112 |
+
"content": "<pad>",
|
| 113 |
+
"lstrip": false,
|
| 114 |
+
"normalized": false,
|
| 115 |
+
"rstrip": false,
|
| 116 |
+
"single_word": false
|
| 117 |
+
},
|
| 118 |
+
"unk_token": {
|
| 119 |
+
"content": "<unk>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false
|
| 124 |
+
}
|
| 125 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,939 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": null,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<pad>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "</s>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "<unk>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"32000": {
|
| 29 |
+
"content": "<extra_id_99>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"32001": {
|
| 37 |
+
"content": "<extra_id_98>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"32002": {
|
| 45 |
+
"content": "<extra_id_97>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"32003": {
|
| 53 |
+
"content": "<extra_id_96>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"32004": {
|
| 61 |
+
"content": "<extra_id_95>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"32005": {
|
| 69 |
+
"content": "<extra_id_94>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"32006": {
|
| 77 |
+
"content": "<extra_id_93>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"32007": {
|
| 85 |
+
"content": "<extra_id_92>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"32008": {
|
| 93 |
+
"content": "<extra_id_91>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"32009": {
|
| 101 |
+
"content": "<extra_id_90>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"32010": {
|
| 109 |
+
"content": "<extra_id_89>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"32011": {
|
| 117 |
+
"content": "<extra_id_88>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": true
|
| 123 |
+
},
|
| 124 |
+
"32012": {
|
| 125 |
+
"content": "<extra_id_87>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
"32013": {
|
| 133 |
+
"content": "<extra_id_86>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": true
|
| 139 |
+
},
|
| 140 |
+
"32014": {
|
| 141 |
+
"content": "<extra_id_85>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": true
|
| 147 |
+
},
|
| 148 |
+
"32015": {
|
| 149 |
+
"content": "<extra_id_84>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": true
|
| 155 |
+
},
|
| 156 |
+
"32016": {
|
| 157 |
+
"content": "<extra_id_83>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": true
|
| 163 |
+
},
|
| 164 |
+
"32017": {
|
| 165 |
+
"content": "<extra_id_82>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": true
|
| 171 |
+
},
|
| 172 |
+
"32018": {
|
| 173 |
+
"content": "<extra_id_81>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": true
|
| 179 |
+
},
|
| 180 |
+
"32019": {
|
| 181 |
+
"content": "<extra_id_80>",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": true
|
| 187 |
+
},
|
| 188 |
+
"32020": {
|
| 189 |
+
"content": "<extra_id_79>",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": false,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": true
|
| 195 |
+
},
|
| 196 |
+
"32021": {
|
| 197 |
+
"content": "<extra_id_78>",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": false,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": true
|
| 203 |
+
},
|
| 204 |
+
"32022": {
|
| 205 |
+
"content": "<extra_id_77>",
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"normalized": false,
|
| 208 |
+
"rstrip": false,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": true
|
| 211 |
+
},
|
| 212 |
+
"32023": {
|
| 213 |
+
"content": "<extra_id_76>",
|
| 214 |
+
"lstrip": false,
|
| 215 |
+
"normalized": false,
|
| 216 |
+
"rstrip": false,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": true
|
| 219 |
+
},
|
| 220 |
+
"32024": {
|
| 221 |
+
"content": "<extra_id_75>",
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"normalized": false,
|
| 224 |
+
"rstrip": false,
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"special": true
|
| 227 |
+
},
|
| 228 |
+
"32025": {
|
| 229 |
+
"content": "<extra_id_74>",
|
| 230 |
+
"lstrip": false,
|
| 231 |
+
"normalized": false,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"single_word": false,
|
| 234 |
+
"special": true
|
| 235 |
+
},
|
| 236 |
+
"32026": {
|
| 237 |
+
"content": "<extra_id_73>",
|
| 238 |
+
"lstrip": false,
|
| 239 |
+
"normalized": false,
|
| 240 |
+
"rstrip": false,
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"special": true
|
| 243 |
+
},
|
| 244 |
+
"32027": {
|
| 245 |
+
"content": "<extra_id_72>",
|
| 246 |
+
"lstrip": false,
|
| 247 |
+
"normalized": false,
|
| 248 |
+
"rstrip": false,
|
| 249 |
+
"single_word": false,
|
| 250 |
+
"special": true
|
| 251 |
+
},
|
| 252 |
+
"32028": {
|
| 253 |
+
"content": "<extra_id_71>",
|
| 254 |
+
"lstrip": false,
|
| 255 |
+
"normalized": false,
|
| 256 |
+
"rstrip": false,
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"special": true
|
| 259 |
+
},
|
| 260 |
+
"32029": {
|
| 261 |
+
"content": "<extra_id_70>",
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"normalized": false,
|
| 264 |
+
"rstrip": false,
|
| 265 |
+
"single_word": false,
|
| 266 |
+
"special": true
|
| 267 |
+
},
|
| 268 |
+
"32030": {
|
| 269 |
+
"content": "<extra_id_69>",
|
| 270 |
+
"lstrip": false,
|
| 271 |
+
"normalized": false,
|
| 272 |
+
"rstrip": false,
|
| 273 |
+
"single_word": false,
|
| 274 |
+
"special": true
|
| 275 |
+
},
|
| 276 |
+
"32031": {
|
| 277 |
+
"content": "<extra_id_68>",
|
| 278 |
+
"lstrip": false,
|
| 279 |
+
"normalized": false,
|
| 280 |
+
"rstrip": false,
|
| 281 |
+
"single_word": false,
|
| 282 |
+
"special": true
|
| 283 |
+
},
|
| 284 |
+
"32032": {
|
| 285 |
+
"content": "<extra_id_67>",
|
| 286 |
+
"lstrip": false,
|
| 287 |
+
"normalized": false,
|
| 288 |
+
"rstrip": false,
|
| 289 |
+
"single_word": false,
|
| 290 |
+
"special": true
|
| 291 |
+
},
|
| 292 |
+
"32033": {
|
| 293 |
+
"content": "<extra_id_66>",
|
| 294 |
+
"lstrip": false,
|
| 295 |
+
"normalized": false,
|
| 296 |
+
"rstrip": false,
|
| 297 |
+
"single_word": false,
|
| 298 |
+
"special": true
|
| 299 |
+
},
|
| 300 |
+
"32034": {
|
| 301 |
+
"content": "<extra_id_65>",
|
| 302 |
+
"lstrip": false,
|
| 303 |
+
"normalized": false,
|
| 304 |
+
"rstrip": false,
|
| 305 |
+
"single_word": false,
|
| 306 |
+
"special": true
|
| 307 |
+
},
|
| 308 |
+
"32035": {
|
| 309 |
+
"content": "<extra_id_64>",
|
| 310 |
+
"lstrip": false,
|
| 311 |
+
"normalized": false,
|
| 312 |
+
"rstrip": false,
|
| 313 |
+
"single_word": false,
|
| 314 |
+
"special": true
|
| 315 |
+
},
|
| 316 |
+
"32036": {
|
| 317 |
+
"content": "<extra_id_63>",
|
| 318 |
+
"lstrip": false,
|
| 319 |
+
"normalized": false,
|
| 320 |
+
"rstrip": false,
|
| 321 |
+
"single_word": false,
|
| 322 |
+
"special": true
|
| 323 |
+
},
|
| 324 |
+
"32037": {
|
| 325 |
+
"content": "<extra_id_62>",
|
| 326 |
+
"lstrip": false,
|
| 327 |
+
"normalized": false,
|
| 328 |
+
"rstrip": false,
|
| 329 |
+
"single_word": false,
|
| 330 |
+
"special": true
|
| 331 |
+
},
|
| 332 |
+
"32038": {
|
| 333 |
+
"content": "<extra_id_61>",
|
| 334 |
+
"lstrip": false,
|
| 335 |
+
"normalized": false,
|
| 336 |
+
"rstrip": false,
|
| 337 |
+
"single_word": false,
|
| 338 |
+
"special": true
|
| 339 |
+
},
|
| 340 |
+
"32039": {
|
| 341 |
+
"content": "<extra_id_60>",
|
| 342 |
+
"lstrip": false,
|
| 343 |
+
"normalized": false,
|
| 344 |
+
"rstrip": false,
|
| 345 |
+
"single_word": false,
|
| 346 |
+
"special": true
|
| 347 |
+
},
|
| 348 |
+
"32040": {
|
| 349 |
+
"content": "<extra_id_59>",
|
| 350 |
+
"lstrip": false,
|
| 351 |
+
"normalized": false,
|
| 352 |
+
"rstrip": false,
|
| 353 |
+
"single_word": false,
|
| 354 |
+
"special": true
|
| 355 |
+
},
|
| 356 |
+
"32041": {
|
| 357 |
+
"content": "<extra_id_58>",
|
| 358 |
+
"lstrip": false,
|
| 359 |
+
"normalized": false,
|
| 360 |
+
"rstrip": false,
|
| 361 |
+
"single_word": false,
|
| 362 |
+
"special": true
|
| 363 |
+
},
|
| 364 |
+
"32042": {
|
| 365 |
+
"content": "<extra_id_57>",
|
| 366 |
+
"lstrip": false,
|
| 367 |
+
"normalized": false,
|
| 368 |
+
"rstrip": false,
|
| 369 |
+
"single_word": false,
|
| 370 |
+
"special": true
|
| 371 |
+
},
|
| 372 |
+
"32043": {
|
| 373 |
+
"content": "<extra_id_56>",
|
| 374 |
+
"lstrip": false,
|
| 375 |
+
"normalized": false,
|
| 376 |
+
"rstrip": false,
|
| 377 |
+
"single_word": false,
|
| 378 |
+
"special": true
|
| 379 |
+
},
|
| 380 |
+
"32044": {
|
| 381 |
+
"content": "<extra_id_55>",
|
| 382 |
+
"lstrip": false,
|
| 383 |
+
"normalized": false,
|
| 384 |
+
"rstrip": false,
|
| 385 |
+
"single_word": false,
|
| 386 |
+
"special": true
|
| 387 |
+
},
|
| 388 |
+
"32045": {
|
| 389 |
+
"content": "<extra_id_54>",
|
| 390 |
+
"lstrip": false,
|
| 391 |
+
"normalized": false,
|
| 392 |
+
"rstrip": false,
|
| 393 |
+
"single_word": false,
|
| 394 |
+
"special": true
|
| 395 |
+
},
|
| 396 |
+
"32046": {
|
| 397 |
+
"content": "<extra_id_53>",
|
| 398 |
+
"lstrip": false,
|
| 399 |
+
"normalized": false,
|
| 400 |
+
"rstrip": false,
|
| 401 |
+
"single_word": false,
|
| 402 |
+
"special": true
|
| 403 |
+
},
|
| 404 |
+
"32047": {
|
| 405 |
+
"content": "<extra_id_52>",
|
| 406 |
+
"lstrip": false,
|
| 407 |
+
"normalized": false,
|
| 408 |
+
"rstrip": false,
|
| 409 |
+
"single_word": false,
|
| 410 |
+
"special": true
|
| 411 |
+
},
|
| 412 |
+
"32048": {
|
| 413 |
+
"content": "<extra_id_51>",
|
| 414 |
+
"lstrip": false,
|
| 415 |
+
"normalized": false,
|
| 416 |
+
"rstrip": false,
|
| 417 |
+
"single_word": false,
|
| 418 |
+
"special": true
|
| 419 |
+
},
|
| 420 |
+
"32049": {
|
| 421 |
+
"content": "<extra_id_50>",
|
| 422 |
+
"lstrip": false,
|
| 423 |
+
"normalized": false,
|
| 424 |
+
"rstrip": false,
|
| 425 |
+
"single_word": false,
|
| 426 |
+
"special": true
|
| 427 |
+
},
|
| 428 |
+
"32050": {
|
| 429 |
+
"content": "<extra_id_49>",
|
| 430 |
+
"lstrip": false,
|
| 431 |
+
"normalized": false,
|
| 432 |
+
"rstrip": false,
|
| 433 |
+
"single_word": false,
|
| 434 |
+
"special": true
|
| 435 |
+
},
|
| 436 |
+
"32051": {
|
| 437 |
+
"content": "<extra_id_48>",
|
| 438 |
+
"lstrip": false,
|
| 439 |
+
"normalized": false,
|
| 440 |
+
"rstrip": false,
|
| 441 |
+
"single_word": false,
|
| 442 |
+
"special": true
|
| 443 |
+
},
|
| 444 |
+
"32052": {
|
| 445 |
+
"content": "<extra_id_47>",
|
| 446 |
+
"lstrip": false,
|
| 447 |
+
"normalized": false,
|
| 448 |
+
"rstrip": false,
|
| 449 |
+
"single_word": false,
|
| 450 |
+
"special": true
|
| 451 |
+
},
|
| 452 |
+
"32053": {
|
| 453 |
+
"content": "<extra_id_46>",
|
| 454 |
+
"lstrip": false,
|
| 455 |
+
"normalized": false,
|
| 456 |
+
"rstrip": false,
|
| 457 |
+
"single_word": false,
|
| 458 |
+
"special": true
|
| 459 |
+
},
|
| 460 |
+
"32054": {
|
| 461 |
+
"content": "<extra_id_45>",
|
| 462 |
+
"lstrip": false,
|
| 463 |
+
"normalized": false,
|
| 464 |
+
"rstrip": false,
|
| 465 |
+
"single_word": false,
|
| 466 |
+
"special": true
|
| 467 |
+
},
|
| 468 |
+
"32055": {
|
| 469 |
+
"content": "<extra_id_44>",
|
| 470 |
+
"lstrip": false,
|
| 471 |
+
"normalized": false,
|
| 472 |
+
"rstrip": false,
|
| 473 |
+
"single_word": false,
|
| 474 |
+
"special": true
|
| 475 |
+
},
|
| 476 |
+
"32056": {
|
| 477 |
+
"content": "<extra_id_43>",
|
| 478 |
+
"lstrip": false,
|
| 479 |
+
"normalized": false,
|
| 480 |
+
"rstrip": false,
|
| 481 |
+
"single_word": false,
|
| 482 |
+
"special": true
|
| 483 |
+
},
|
| 484 |
+
"32057": {
|
| 485 |
+
"content": "<extra_id_42>",
|
| 486 |
+
"lstrip": false,
|
| 487 |
+
"normalized": false,
|
| 488 |
+
"rstrip": false,
|
| 489 |
+
"single_word": false,
|
| 490 |
+
"special": true
|
| 491 |
+
},
|
| 492 |
+
"32058": {
|
| 493 |
+
"content": "<extra_id_41>",
|
| 494 |
+
"lstrip": false,
|
| 495 |
+
"normalized": false,
|
| 496 |
+
"rstrip": false,
|
| 497 |
+
"single_word": false,
|
| 498 |
+
"special": true
|
| 499 |
+
},
|
| 500 |
+
"32059": {
|
| 501 |
+
"content": "<extra_id_40>",
|
| 502 |
+
"lstrip": false,
|
| 503 |
+
"normalized": false,
|
| 504 |
+
"rstrip": false,
|
| 505 |
+
"single_word": false,
|
| 506 |
+
"special": true
|
| 507 |
+
},
|
| 508 |
+
"32060": {
|
| 509 |
+
"content": "<extra_id_39>",
|
| 510 |
+
"lstrip": false,
|
| 511 |
+
"normalized": false,
|
| 512 |
+
"rstrip": false,
|
| 513 |
+
"single_word": false,
|
| 514 |
+
"special": true
|
| 515 |
+
},
|
| 516 |
+
"32061": {
|
| 517 |
+
"content": "<extra_id_38>",
|
| 518 |
+
"lstrip": false,
|
| 519 |
+
"normalized": false,
|
| 520 |
+
"rstrip": false,
|
| 521 |
+
"single_word": false,
|
| 522 |
+
"special": true
|
| 523 |
+
},
|
| 524 |
+
"32062": {
|
| 525 |
+
"content": "<extra_id_37>",
|
| 526 |
+
"lstrip": false,
|
| 527 |
+
"normalized": false,
|
| 528 |
+
"rstrip": false,
|
| 529 |
+
"single_word": false,
|
| 530 |
+
"special": true
|
| 531 |
+
},
|
| 532 |
+
"32063": {
|
| 533 |
+
"content": "<extra_id_36>",
|
| 534 |
+
"lstrip": false,
|
| 535 |
+
"normalized": false,
|
| 536 |
+
"rstrip": false,
|
| 537 |
+
"single_word": false,
|
| 538 |
+
"special": true
|
| 539 |
+
},
|
| 540 |
+
"32064": {
|
| 541 |
+
"content": "<extra_id_35>",
|
| 542 |
+
"lstrip": false,
|
| 543 |
+
"normalized": false,
|
| 544 |
+
"rstrip": false,
|
| 545 |
+
"single_word": false,
|
| 546 |
+
"special": true
|
| 547 |
+
},
|
| 548 |
+
"32065": {
|
| 549 |
+
"content": "<extra_id_34>",
|
| 550 |
+
"lstrip": false,
|
| 551 |
+
"normalized": false,
|
| 552 |
+
"rstrip": false,
|
| 553 |
+
"single_word": false,
|
| 554 |
+
"special": true
|
| 555 |
+
},
|
| 556 |
+
"32066": {
|
| 557 |
+
"content": "<extra_id_33>",
|
| 558 |
+
"lstrip": false,
|
| 559 |
+
"normalized": false,
|
| 560 |
+
"rstrip": false,
|
| 561 |
+
"single_word": false,
|
| 562 |
+
"special": true
|
| 563 |
+
},
|
| 564 |
+
"32067": {
|
| 565 |
+
"content": "<extra_id_32>",
|
| 566 |
+
"lstrip": false,
|
| 567 |
+
"normalized": false,
|
| 568 |
+
"rstrip": false,
|
| 569 |
+
"single_word": false,
|
| 570 |
+
"special": true
|
| 571 |
+
},
|
| 572 |
+
"32068": {
|
| 573 |
+
"content": "<extra_id_31>",
|
| 574 |
+
"lstrip": false,
|
| 575 |
+
"normalized": false,
|
| 576 |
+
"rstrip": false,
|
| 577 |
+
"single_word": false,
|
| 578 |
+
"special": true
|
| 579 |
+
},
|
| 580 |
+
"32069": {
|
| 581 |
+
"content": "<extra_id_30>",
|
| 582 |
+
"lstrip": false,
|
| 583 |
+
"normalized": false,
|
| 584 |
+
"rstrip": false,
|
| 585 |
+
"single_word": false,
|
| 586 |
+
"special": true
|
| 587 |
+
},
|
| 588 |
+
"32070": {
|
| 589 |
+
"content": "<extra_id_29>",
|
| 590 |
+
"lstrip": false,
|
| 591 |
+
"normalized": false,
|
| 592 |
+
"rstrip": false,
|
| 593 |
+
"single_word": false,
|
| 594 |
+
"special": true
|
| 595 |
+
},
|
| 596 |
+
"32071": {
|
| 597 |
+
"content": "<extra_id_28>",
|
| 598 |
+
"lstrip": false,
|
| 599 |
+
"normalized": false,
|
| 600 |
+
"rstrip": false,
|
| 601 |
+
"single_word": false,
|
| 602 |
+
"special": true
|
| 603 |
+
},
|
| 604 |
+
"32072": {
|
| 605 |
+
"content": "<extra_id_27>",
|
| 606 |
+
"lstrip": false,
|
| 607 |
+
"normalized": false,
|
| 608 |
+
"rstrip": false,
|
| 609 |
+
"single_word": false,
|
| 610 |
+
"special": true
|
| 611 |
+
},
|
| 612 |
+
"32073": {
|
| 613 |
+
"content": "<extra_id_26>",
|
| 614 |
+
"lstrip": false,
|
| 615 |
+
"normalized": false,
|
| 616 |
+
"rstrip": false,
|
| 617 |
+
"single_word": false,
|
| 618 |
+
"special": true
|
| 619 |
+
},
|
| 620 |
+
"32074": {
|
| 621 |
+
"content": "<extra_id_25>",
|
| 622 |
+
"lstrip": false,
|
| 623 |
+
"normalized": false,
|
| 624 |
+
"rstrip": false,
|
| 625 |
+
"single_word": false,
|
| 626 |
+
"special": true
|
| 627 |
+
},
|
| 628 |
+
"32075": {
|
| 629 |
+
"content": "<extra_id_24>",
|
| 630 |
+
"lstrip": false,
|
| 631 |
+
"normalized": false,
|
| 632 |
+
"rstrip": false,
|
| 633 |
+
"single_word": false,
|
| 634 |
+
"special": true
|
| 635 |
+
},
|
| 636 |
+
"32076": {
|
| 637 |
+
"content": "<extra_id_23>",
|
| 638 |
+
"lstrip": false,
|
| 639 |
+
"normalized": false,
|
| 640 |
+
"rstrip": false,
|
| 641 |
+
"single_word": false,
|
| 642 |
+
"special": true
|
| 643 |
+
},
|
| 644 |
+
"32077": {
|
| 645 |
+
"content": "<extra_id_22>",
|
| 646 |
+
"lstrip": false,
|
| 647 |
+
"normalized": false,
|
| 648 |
+
"rstrip": false,
|
| 649 |
+
"single_word": false,
|
| 650 |
+
"special": true
|
| 651 |
+
},
|
| 652 |
+
"32078": {
|
| 653 |
+
"content": "<extra_id_21>",
|
| 654 |
+
"lstrip": false,
|
| 655 |
+
"normalized": false,
|
| 656 |
+
"rstrip": false,
|
| 657 |
+
"single_word": false,
|
| 658 |
+
"special": true
|
| 659 |
+
},
|
| 660 |
+
"32079": {
|
| 661 |
+
"content": "<extra_id_20>",
|
| 662 |
+
"lstrip": false,
|
| 663 |
+
"normalized": false,
|
| 664 |
+
"rstrip": false,
|
| 665 |
+
"single_word": false,
|
| 666 |
+
"special": true
|
| 667 |
+
},
|
| 668 |
+
"32080": {
|
| 669 |
+
"content": "<extra_id_19>",
|
| 670 |
+
"lstrip": false,
|
| 671 |
+
"normalized": false,
|
| 672 |
+
"rstrip": false,
|
| 673 |
+
"single_word": false,
|
| 674 |
+
"special": true
|
| 675 |
+
},
|
| 676 |
+
"32081": {
|
| 677 |
+
"content": "<extra_id_18>",
|
| 678 |
+
"lstrip": false,
|
| 679 |
+
"normalized": false,
|
| 680 |
+
"rstrip": false,
|
| 681 |
+
"single_word": false,
|
| 682 |
+
"special": true
|
| 683 |
+
},
|
| 684 |
+
"32082": {
|
| 685 |
+
"content": "<extra_id_17>",
|
| 686 |
+
"lstrip": false,
|
| 687 |
+
"normalized": false,
|
| 688 |
+
"rstrip": false,
|
| 689 |
+
"single_word": false,
|
| 690 |
+
"special": true
|
| 691 |
+
},
|
| 692 |
+
"32083": {
|
| 693 |
+
"content": "<extra_id_16>",
|
| 694 |
+
"lstrip": false,
|
| 695 |
+
"normalized": false,
|
| 696 |
+
"rstrip": false,
|
| 697 |
+
"single_word": false,
|
| 698 |
+
"special": true
|
| 699 |
+
},
|
| 700 |
+
"32084": {
|
| 701 |
+
"content": "<extra_id_15>",
|
| 702 |
+
"lstrip": false,
|
| 703 |
+
"normalized": false,
|
| 704 |
+
"rstrip": false,
|
| 705 |
+
"single_word": false,
|
| 706 |
+
"special": true
|
| 707 |
+
},
|
| 708 |
+
"32085": {
|
| 709 |
+
"content": "<extra_id_14>",
|
| 710 |
+
"lstrip": false,
|
| 711 |
+
"normalized": false,
|
| 712 |
+
"rstrip": false,
|
| 713 |
+
"single_word": false,
|
| 714 |
+
"special": true
|
| 715 |
+
},
|
| 716 |
+
"32086": {
|
| 717 |
+
"content": "<extra_id_13>",
|
| 718 |
+
"lstrip": false,
|
| 719 |
+
"normalized": false,
|
| 720 |
+
"rstrip": false,
|
| 721 |
+
"single_word": false,
|
| 722 |
+
"special": true
|
| 723 |
+
},
|
| 724 |
+
"32087": {
|
| 725 |
+
"content": "<extra_id_12>",
|
| 726 |
+
"lstrip": false,
|
| 727 |
+
"normalized": false,
|
| 728 |
+
"rstrip": false,
|
| 729 |
+
"single_word": false,
|
| 730 |
+
"special": true
|
| 731 |
+
},
|
| 732 |
+
"32088": {
|
| 733 |
+
"content": "<extra_id_11>",
|
| 734 |
+
"lstrip": false,
|
| 735 |
+
"normalized": false,
|
| 736 |
+
"rstrip": false,
|
| 737 |
+
"single_word": false,
|
| 738 |
+
"special": true
|
| 739 |
+
},
|
| 740 |
+
"32089": {
|
| 741 |
+
"content": "<extra_id_10>",
|
| 742 |
+
"lstrip": false,
|
| 743 |
+
"normalized": false,
|
| 744 |
+
"rstrip": false,
|
| 745 |
+
"single_word": false,
|
| 746 |
+
"special": true
|
| 747 |
+
},
|
| 748 |
+
"32090": {
|
| 749 |
+
"content": "<extra_id_9>",
|
| 750 |
+
"lstrip": false,
|
| 751 |
+
"normalized": false,
|
| 752 |
+
"rstrip": false,
|
| 753 |
+
"single_word": false,
|
| 754 |
+
"special": true
|
| 755 |
+
},
|
| 756 |
+
"32091": {
|
| 757 |
+
"content": "<extra_id_8>",
|
| 758 |
+
"lstrip": false,
|
| 759 |
+
"normalized": false,
|
| 760 |
+
"rstrip": false,
|
| 761 |
+
"single_word": false,
|
| 762 |
+
"special": true
|
| 763 |
+
},
|
| 764 |
+
"32092": {
|
| 765 |
+
"content": "<extra_id_7>",
|
| 766 |
+
"lstrip": false,
|
| 767 |
+
"normalized": false,
|
| 768 |
+
"rstrip": false,
|
| 769 |
+
"single_word": false,
|
| 770 |
+
"special": true
|
| 771 |
+
},
|
| 772 |
+
"32093": {
|
| 773 |
+
"content": "<extra_id_6>",
|
| 774 |
+
"lstrip": false,
|
| 775 |
+
"normalized": false,
|
| 776 |
+
"rstrip": false,
|
| 777 |
+
"single_word": false,
|
| 778 |
+
"special": true
|
| 779 |
+
},
|
| 780 |
+
"32094": {
|
| 781 |
+
"content": "<extra_id_5>",
|
| 782 |
+
"lstrip": false,
|
| 783 |
+
"normalized": false,
|
| 784 |
+
"rstrip": false,
|
| 785 |
+
"single_word": false,
|
| 786 |
+
"special": true
|
| 787 |
+
},
|
| 788 |
+
"32095": {
|
| 789 |
+
"content": "<extra_id_4>",
|
| 790 |
+
"lstrip": false,
|
| 791 |
+
"normalized": false,
|
| 792 |
+
"rstrip": false,
|
| 793 |
+
"single_word": false,
|
| 794 |
+
"special": true
|
| 795 |
+
},
|
| 796 |
+
"32096": {
|
| 797 |
+
"content": "<extra_id_3>",
|
| 798 |
+
"lstrip": false,
|
| 799 |
+
"normalized": false,
|
| 800 |
+
"rstrip": false,
|
| 801 |
+
"single_word": false,
|
| 802 |
+
"special": true
|
| 803 |
+
},
|
| 804 |
+
"32097": {
|
| 805 |
+
"content": "<extra_id_2>",
|
| 806 |
+
"lstrip": false,
|
| 807 |
+
"normalized": false,
|
| 808 |
+
"rstrip": false,
|
| 809 |
+
"single_word": false,
|
| 810 |
+
"special": true
|
| 811 |
+
},
|
| 812 |
+
"32098": {
|
| 813 |
+
"content": "<extra_id_1>",
|
| 814 |
+
"lstrip": false,
|
| 815 |
+
"normalized": false,
|
| 816 |
+
"rstrip": false,
|
| 817 |
+
"single_word": false,
|
| 818 |
+
"special": true
|
| 819 |
+
},
|
| 820 |
+
"32099": {
|
| 821 |
+
"content": "<extra_id_0>",
|
| 822 |
+
"lstrip": false,
|
| 823 |
+
"normalized": false,
|
| 824 |
+
"rstrip": false,
|
| 825 |
+
"single_word": false,
|
| 826 |
+
"special": true
|
| 827 |
+
}
|
| 828 |
+
},
|
| 829 |
+
"additional_special_tokens": [
|
| 830 |
+
"<extra_id_0>",
|
| 831 |
+
"<extra_id_1>",
|
| 832 |
+
"<extra_id_2>",
|
| 833 |
+
"<extra_id_3>",
|
| 834 |
+
"<extra_id_4>",
|
| 835 |
+
"<extra_id_5>",
|
| 836 |
+
"<extra_id_6>",
|
| 837 |
+
"<extra_id_7>",
|
| 838 |
+
"<extra_id_8>",
|
| 839 |
+
"<extra_id_9>",
|
| 840 |
+
"<extra_id_10>",
|
| 841 |
+
"<extra_id_11>",
|
| 842 |
+
"<extra_id_12>",
|
| 843 |
+
"<extra_id_13>",
|
| 844 |
+
"<extra_id_14>",
|
| 845 |
+
"<extra_id_15>",
|
| 846 |
+
"<extra_id_16>",
|
| 847 |
+
"<extra_id_17>",
|
| 848 |
+
"<extra_id_18>",
|
| 849 |
+
"<extra_id_19>",
|
| 850 |
+
"<extra_id_20>",
|
| 851 |
+
"<extra_id_21>",
|
| 852 |
+
"<extra_id_22>",
|
| 853 |
+
"<extra_id_23>",
|
| 854 |
+
"<extra_id_24>",
|
| 855 |
+
"<extra_id_25>",
|
| 856 |
+
"<extra_id_26>",
|
| 857 |
+
"<extra_id_27>",
|
| 858 |
+
"<extra_id_28>",
|
| 859 |
+
"<extra_id_29>",
|
| 860 |
+
"<extra_id_30>",
|
| 861 |
+
"<extra_id_31>",
|
| 862 |
+
"<extra_id_32>",
|
| 863 |
+
"<extra_id_33>",
|
| 864 |
+
"<extra_id_34>",
|
| 865 |
+
"<extra_id_35>",
|
| 866 |
+
"<extra_id_36>",
|
| 867 |
+
"<extra_id_37>",
|
| 868 |
+
"<extra_id_38>",
|
| 869 |
+
"<extra_id_39>",
|
| 870 |
+
"<extra_id_40>",
|
| 871 |
+
"<extra_id_41>",
|
| 872 |
+
"<extra_id_42>",
|
| 873 |
+
"<extra_id_43>",
|
| 874 |
+
"<extra_id_44>",
|
| 875 |
+
"<extra_id_45>",
|
| 876 |
+
"<extra_id_46>",
|
| 877 |
+
"<extra_id_47>",
|
| 878 |
+
"<extra_id_48>",
|
| 879 |
+
"<extra_id_49>",
|
| 880 |
+
"<extra_id_50>",
|
| 881 |
+
"<extra_id_51>",
|
| 882 |
+
"<extra_id_52>",
|
| 883 |
+
"<extra_id_53>",
|
| 884 |
+
"<extra_id_54>",
|
| 885 |
+
"<extra_id_55>",
|
| 886 |
+
"<extra_id_56>",
|
| 887 |
+
"<extra_id_57>",
|
| 888 |
+
"<extra_id_58>",
|
| 889 |
+
"<extra_id_59>",
|
| 890 |
+
"<extra_id_60>",
|
| 891 |
+
"<extra_id_61>",
|
| 892 |
+
"<extra_id_62>",
|
| 893 |
+
"<extra_id_63>",
|
| 894 |
+
"<extra_id_64>",
|
| 895 |
+
"<extra_id_65>",
|
| 896 |
+
"<extra_id_66>",
|
| 897 |
+
"<extra_id_67>",
|
| 898 |
+
"<extra_id_68>",
|
| 899 |
+
"<extra_id_69>",
|
| 900 |
+
"<extra_id_70>",
|
| 901 |
+
"<extra_id_71>",
|
| 902 |
+
"<extra_id_72>",
|
| 903 |
+
"<extra_id_73>",
|
| 904 |
+
"<extra_id_74>",
|
| 905 |
+
"<extra_id_75>",
|
| 906 |
+
"<extra_id_76>",
|
| 907 |
+
"<extra_id_77>",
|
| 908 |
+
"<extra_id_78>",
|
| 909 |
+
"<extra_id_79>",
|
| 910 |
+
"<extra_id_80>",
|
| 911 |
+
"<extra_id_81>",
|
| 912 |
+
"<extra_id_82>",
|
| 913 |
+
"<extra_id_83>",
|
| 914 |
+
"<extra_id_84>",
|
| 915 |
+
"<extra_id_85>",
|
| 916 |
+
"<extra_id_86>",
|
| 917 |
+
"<extra_id_87>",
|
| 918 |
+
"<extra_id_88>",
|
| 919 |
+
"<extra_id_89>",
|
| 920 |
+
"<extra_id_90>",
|
| 921 |
+
"<extra_id_91>",
|
| 922 |
+
"<extra_id_92>",
|
| 923 |
+
"<extra_id_93>",
|
| 924 |
+
"<extra_id_94>",
|
| 925 |
+
"<extra_id_95>",
|
| 926 |
+
"<extra_id_96>",
|
| 927 |
+
"<extra_id_97>",
|
| 928 |
+
"<extra_id_98>",
|
| 929 |
+
"<extra_id_99>"
|
| 930 |
+
],
|
| 931 |
+
"clean_up_tokenization_spaces": true,
|
| 932 |
+
"eos_token": "</s>",
|
| 933 |
+
"extra_ids": 100,
|
| 934 |
+
"extra_special_tokens": {},
|
| 935 |
+
"model_max_length": 512,
|
| 936 |
+
"pad_token": "<pad>",
|
| 937 |
+
"tokenizer_class": "T5Tokenizer",
|
| 938 |
+
"unk_token": "<unk>"
|
| 939 |
+
}
|