Sentence Similarity
sentence-transformers
Safetensors
mpnet
feature-extraction
Generated from Trainer
dataset_size:3320
loss:MultipleNegativesRankingLoss
loss:CosineSimilarityLoss
Eval Results (legacy)
text-embeddings-inference
Instructions to use Bharatdeep-H/pq_cache with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use Bharatdeep-H/pq_cache with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Bharatdeep-H/pq_cache") sentences = [ "How did my portfolio perform during the last 18 days?", "What is the performance of my portfolio over the last 18 days?", "Show me the geographic distribution of my investments\n", "Show me recommendations on improving returns and risk" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
Upload query normalization model
Browse files- 1_Pooling/config.json +10 -0
- README.md +490 -0
- config.json +24 -0
- config_sentence_transformers.json +10 -0
- eval/Information-Retrieval_evaluation_test-eval_results.csv +11 -0
- model.safetensors +3 -0
- modules.json +20 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +73 -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 +1,490 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- sentence-transformers
|
| 4 |
+
- sentence-similarity
|
| 5 |
+
- feature-extraction
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
- dataset_size:3320
|
| 8 |
+
- loss:MultipleNegativesRankingLoss
|
| 9 |
+
- loss:CosineSimilarityLoss
|
| 10 |
+
base_model: sentence-transformers/all-mpnet-base-v2
|
| 11 |
+
widget:
|
| 12 |
+
- source_sentence: How did my portfolio perform during the last 18 days?
|
| 13 |
+
sentences:
|
| 14 |
+
- What is the performance of my portfolio over the last 18 days?
|
| 15 |
+
- 'Show me the geographic distribution of my investments
|
| 16 |
+
|
| 17 |
+
'
|
| 18 |
+
- Show me recommendations on improving returns and risk
|
| 19 |
+
- source_sentence: I'd like to know my sector distribution.
|
| 20 |
+
sentences:
|
| 21 |
+
- Show my market cap breakdown
|
| 22 |
+
- In which funds am I paying highest fees
|
| 23 |
+
- What is my sector allocation?
|
| 24 |
+
- source_sentence: Do I have any equity funds in my portfolio?
|
| 25 |
+
sentences:
|
| 26 |
+
- Show me my recommendations
|
| 27 |
+
- Do I hold any equity funds?
|
| 28 |
+
- Show me some swap recommendations on my portfolio
|
| 29 |
+
- source_sentence: Is my portfolio ready for changes in the market?
|
| 30 |
+
sentences:
|
| 31 |
+
- Is my current portfolio balanced properly for market changes?
|
| 32 |
+
- Have I got Swap recommendations on risk
|
| 33 |
+
- is there any room for improvement in my portfolio
|
| 34 |
+
- source_sentence: Which stocks would be best to trade for funds?
|
| 35 |
+
sentences:
|
| 36 |
+
- Is my portfolio beating the market?
|
| 37 |
+
- Show me ways to reduce my cost
|
| 38 |
+
- Which of my stocks should I swap for funds?
|
| 39 |
+
pipeline_tag: sentence-similarity
|
| 40 |
+
library_name: sentence-transformers
|
| 41 |
+
metrics:
|
| 42 |
+
- cosine_accuracy@1
|
| 43 |
+
- cosine_accuracy@3
|
| 44 |
+
- cosine_accuracy@5
|
| 45 |
+
- cosine_accuracy@10
|
| 46 |
+
- cosine_precision@1
|
| 47 |
+
- cosine_precision@3
|
| 48 |
+
- cosine_precision@5
|
| 49 |
+
- cosine_precision@10
|
| 50 |
+
- cosine_recall@1
|
| 51 |
+
- cosine_recall@3
|
| 52 |
+
- cosine_recall@5
|
| 53 |
+
- cosine_recall@10
|
| 54 |
+
- cosine_ndcg@10
|
| 55 |
+
- cosine_mrr@10
|
| 56 |
+
- cosine_map@100
|
| 57 |
+
model-index:
|
| 58 |
+
- name: SentenceTransformer based on sentence-transformers/all-mpnet-base-v2
|
| 59 |
+
results:
|
| 60 |
+
- task:
|
| 61 |
+
type: information-retrieval
|
| 62 |
+
name: Information Retrieval
|
| 63 |
+
dataset:
|
| 64 |
+
name: test eval
|
| 65 |
+
type: test-eval
|
| 66 |
+
metrics:
|
| 67 |
+
- type: cosine_accuracy@1
|
| 68 |
+
value: 0.8975903614457831
|
| 69 |
+
name: Cosine Accuracy@1
|
| 70 |
+
- type: cosine_accuracy@3
|
| 71 |
+
value: 0.9969879518072289
|
| 72 |
+
name: Cosine Accuracy@3
|
| 73 |
+
- type: cosine_accuracy@5
|
| 74 |
+
value: 1.0
|
| 75 |
+
name: Cosine Accuracy@5
|
| 76 |
+
- type: cosine_accuracy@10
|
| 77 |
+
value: 1.0
|
| 78 |
+
name: Cosine Accuracy@10
|
| 79 |
+
- type: cosine_precision@1
|
| 80 |
+
value: 0.8975903614457831
|
| 81 |
+
name: Cosine Precision@1
|
| 82 |
+
- type: cosine_precision@3
|
| 83 |
+
value: 0.33232931726907633
|
| 84 |
+
name: Cosine Precision@3
|
| 85 |
+
- type: cosine_precision@5
|
| 86 |
+
value: 0.19999999999999998
|
| 87 |
+
name: Cosine Precision@5
|
| 88 |
+
- type: cosine_precision@10
|
| 89 |
+
value: 0.09999999999999999
|
| 90 |
+
name: Cosine Precision@10
|
| 91 |
+
- type: cosine_recall@1
|
| 92 |
+
value: 0.8975903614457831
|
| 93 |
+
name: Cosine Recall@1
|
| 94 |
+
- type: cosine_recall@3
|
| 95 |
+
value: 0.9969879518072289
|
| 96 |
+
name: Cosine Recall@3
|
| 97 |
+
- type: cosine_recall@5
|
| 98 |
+
value: 1.0
|
| 99 |
+
name: Cosine Recall@5
|
| 100 |
+
- type: cosine_recall@10
|
| 101 |
+
value: 1.0
|
| 102 |
+
name: Cosine Recall@10
|
| 103 |
+
- type: cosine_ndcg@10
|
| 104 |
+
value: 0.9600230102760412
|
| 105 |
+
name: Cosine Ndcg@10
|
| 106 |
+
- type: cosine_mrr@10
|
| 107 |
+
value: 0.9460341365461847
|
| 108 |
+
name: Cosine Mrr@10
|
| 109 |
+
- type: cosine_map@100
|
| 110 |
+
value: 0.9460341365461847
|
| 111 |
+
name: Cosine Map@100
|
| 112 |
+
---
|
| 113 |
+
|
| 114 |
+
# SentenceTransformer based on sentence-transformers/all-mpnet-base-v2
|
| 115 |
+
|
| 116 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2). 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.
|
| 117 |
+
|
| 118 |
+
## Model Details
|
| 119 |
+
|
| 120 |
+
### Model Description
|
| 121 |
+
- **Model Type:** Sentence Transformer
|
| 122 |
+
- **Base model:** [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) <!-- at revision 12e86a3c702fc3c50205a8db88f0ec7c0b6b94a0 -->
|
| 123 |
+
- **Maximum Sequence Length:** 384 tokens
|
| 124 |
+
- **Output Dimensionality:** 768 dimensions
|
| 125 |
+
- **Similarity Function:** Cosine Similarity
|
| 126 |
+
<!-- - **Training Dataset:** Unknown -->
|
| 127 |
+
<!-- - **Language:** Unknown -->
|
| 128 |
+
<!-- - **License:** Unknown -->
|
| 129 |
+
|
| 130 |
+
### Model Sources
|
| 131 |
+
|
| 132 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
| 133 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
| 134 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
| 135 |
+
|
| 136 |
+
### Full Model Architecture
|
| 137 |
+
|
| 138 |
+
```
|
| 139 |
+
SentenceTransformer(
|
| 140 |
+
(0): Transformer({'max_seq_length': 384, 'do_lower_case': False}) with Transformer model: MPNetModel
|
| 141 |
+
(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})
|
| 142 |
+
(2): Normalize()
|
| 143 |
+
)
|
| 144 |
+
```
|
| 145 |
+
|
| 146 |
+
## Usage
|
| 147 |
+
|
| 148 |
+
### Direct Usage (Sentence Transformers)
|
| 149 |
+
|
| 150 |
+
First install the Sentence Transformers library:
|
| 151 |
+
|
| 152 |
+
```bash
|
| 153 |
+
pip install -U sentence-transformers
|
| 154 |
+
```
|
| 155 |
+
|
| 156 |
+
Then you can load this model and run inference.
|
| 157 |
+
```python
|
| 158 |
+
from sentence_transformers import SentenceTransformer
|
| 159 |
+
|
| 160 |
+
# Download from the 🤗 Hub
|
| 161 |
+
model = SentenceTransformer("sentence_transformers_model_id")
|
| 162 |
+
# Run inference
|
| 163 |
+
sentences = [
|
| 164 |
+
'Which stocks would be best to trade for funds?',
|
| 165 |
+
'Which of my stocks should I swap for funds?',
|
| 166 |
+
'Is my portfolio beating the market?',
|
| 167 |
+
]
|
| 168 |
+
embeddings = model.encode(sentences)
|
| 169 |
+
print(embeddings.shape)
|
| 170 |
+
# [3, 768]
|
| 171 |
+
|
| 172 |
+
# Get the similarity scores for the embeddings
|
| 173 |
+
similarities = model.similarity(embeddings, embeddings)
|
| 174 |
+
print(similarities.shape)
|
| 175 |
+
# [3, 3]
|
| 176 |
+
```
|
| 177 |
+
|
| 178 |
+
<!--
|
| 179 |
+
### Direct Usage (Transformers)
|
| 180 |
+
|
| 181 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
| 182 |
+
|
| 183 |
+
</details>
|
| 184 |
+
-->
|
| 185 |
+
|
| 186 |
+
<!--
|
| 187 |
+
### Downstream Usage (Sentence Transformers)
|
| 188 |
+
|
| 189 |
+
You can finetune this model on your own dataset.
|
| 190 |
+
|
| 191 |
+
<details><summary>Click to expand</summary>
|
| 192 |
+
|
| 193 |
+
</details>
|
| 194 |
+
-->
|
| 195 |
+
|
| 196 |
+
<!--
|
| 197 |
+
### Out-of-Scope Use
|
| 198 |
+
|
| 199 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
| 200 |
+
-->
|
| 201 |
+
|
| 202 |
+
## Evaluation
|
| 203 |
+
|
| 204 |
+
### Metrics
|
| 205 |
+
|
| 206 |
+
#### Information Retrieval
|
| 207 |
+
|
| 208 |
+
* Dataset: `test-eval`
|
| 209 |
+
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
|
| 210 |
+
|
| 211 |
+
| Metric | Value |
|
| 212 |
+
|:--------------------|:---------|
|
| 213 |
+
| cosine_accuracy@1 | 0.8976 |
|
| 214 |
+
| cosine_accuracy@3 | 0.997 |
|
| 215 |
+
| cosine_accuracy@5 | 1.0 |
|
| 216 |
+
| cosine_accuracy@10 | 1.0 |
|
| 217 |
+
| cosine_precision@1 | 0.8976 |
|
| 218 |
+
| cosine_precision@3 | 0.3323 |
|
| 219 |
+
| cosine_precision@5 | 0.2 |
|
| 220 |
+
| cosine_precision@10 | 0.1 |
|
| 221 |
+
| cosine_recall@1 | 0.8976 |
|
| 222 |
+
| cosine_recall@3 | 0.997 |
|
| 223 |
+
| cosine_recall@5 | 1.0 |
|
| 224 |
+
| cosine_recall@10 | 1.0 |
|
| 225 |
+
| **cosine_ndcg@10** | **0.96** |
|
| 226 |
+
| cosine_mrr@10 | 0.946 |
|
| 227 |
+
| cosine_map@100 | 0.946 |
|
| 228 |
+
|
| 229 |
+
<!--
|
| 230 |
+
## Bias, Risks and Limitations
|
| 231 |
+
|
| 232 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
| 233 |
+
-->
|
| 234 |
+
|
| 235 |
+
<!--
|
| 236 |
+
### Recommendations
|
| 237 |
+
|
| 238 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
| 239 |
+
-->
|
| 240 |
+
|
| 241 |
+
## Training Details
|
| 242 |
+
|
| 243 |
+
### Training Datasets
|
| 244 |
+
|
| 245 |
+
#### Unnamed Dataset
|
| 246 |
+
|
| 247 |
+
* Size: 1,660 training samples
|
| 248 |
+
* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code>
|
| 249 |
+
* Approximate statistics based on the first 1000 samples:
|
| 250 |
+
| | sentence_0 | sentence_1 | label |
|
| 251 |
+
|:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:--------------------------------------------------------------|
|
| 252 |
+
| type | string | string | float |
|
| 253 |
+
| details | <ul><li>min: 5 tokens</li><li>mean: 12.06 tokens</li><li>max: 26 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 10.67 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> |
|
| 254 |
+
* Samples:
|
| 255 |
+
| sentence_0 | sentence_1 | label |
|
| 256 |
+
|:----------------------------------------------------------------|:-------------------------------------------------|:-----------------|
|
| 257 |
+
| <code>Please suggest some ideas for me.</code> | <code>Suggest recommendations for me</code> | <code>1.0</code> |
|
| 258 |
+
| <code>Mere paas jo stocks hain unhe dikhaiye</code> | <code>Mujhe apne stocks dikhao</code> | <code>1.0</code> |
|
| 259 |
+
| <code>Is my portfolio performing better than the market?</code> | <code>Is my portfolio beating the market?</code> | <code>1.0</code> |
|
| 260 |
+
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
|
| 261 |
+
```json
|
| 262 |
+
{
|
| 263 |
+
"scale": 20.0,
|
| 264 |
+
"similarity_fct": "cos_sim"
|
| 265 |
+
}
|
| 266 |
+
```
|
| 267 |
+
|
| 268 |
+
#### Unnamed Dataset
|
| 269 |
+
|
| 270 |
+
* Size: 1,660 training samples
|
| 271 |
+
* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code>
|
| 272 |
+
* Approximate statistics based on the first 1000 samples:
|
| 273 |
+
| | sentence_0 | sentence_1 | label |
|
| 274 |
+
|:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:--------------------------------------------------------------|
|
| 275 |
+
| type | string | string | float |
|
| 276 |
+
| details | <ul><li>min: 5 tokens</li><li>mean: 12.12 tokens</li><li>max: 26 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 10.71 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> |
|
| 277 |
+
* Samples:
|
| 278 |
+
| sentence_0 | sentence_1 | label |
|
| 279 |
+
|:---------------------------------------------------------------------|:-------------------------------------------------------|:-----------------|
|
| 280 |
+
| <code>I'd like to see my sector allocation, please.</code> | <code>Can you show my sector allocation?</code> | <code>1.0</code> |
|
| 281 |
+
| <code>Which of my funds are failing to perform?</code> | <code>Which of my funds aren't doing well?</code> | <code>1.0</code> |
|
| 282 |
+
| <code>Can you list my investments based on their ESG ratings?</code> | <code>Show my investments sorted by ESG rating.</code> | <code>1.0</code> |
|
| 283 |
+
* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
|
| 284 |
+
```json
|
| 285 |
+
{
|
| 286 |
+
"loss_fct": "torch.nn.modules.loss.MSELoss"
|
| 287 |
+
}
|
| 288 |
+
```
|
| 289 |
+
|
| 290 |
+
### Training Hyperparameters
|
| 291 |
+
#### Non-Default Hyperparameters
|
| 292 |
+
|
| 293 |
+
- `eval_strategy`: steps
|
| 294 |
+
- `per_device_train_batch_size`: 32
|
| 295 |
+
- `per_device_eval_batch_size`: 32
|
| 296 |
+
- `num_train_epochs`: 10
|
| 297 |
+
- `multi_dataset_batch_sampler`: round_robin
|
| 298 |
+
|
| 299 |
+
#### All Hyperparameters
|
| 300 |
+
<details><summary>Click to expand</summary>
|
| 301 |
+
|
| 302 |
+
- `overwrite_output_dir`: False
|
| 303 |
+
- `do_predict`: False
|
| 304 |
+
- `eval_strategy`: steps
|
| 305 |
+
- `prediction_loss_only`: True
|
| 306 |
+
- `per_device_train_batch_size`: 32
|
| 307 |
+
- `per_device_eval_batch_size`: 32
|
| 308 |
+
- `per_gpu_train_batch_size`: None
|
| 309 |
+
- `per_gpu_eval_batch_size`: None
|
| 310 |
+
- `gradient_accumulation_steps`: 1
|
| 311 |
+
- `eval_accumulation_steps`: None
|
| 312 |
+
- `torch_empty_cache_steps`: None
|
| 313 |
+
- `learning_rate`: 5e-05
|
| 314 |
+
- `weight_decay`: 0.0
|
| 315 |
+
- `adam_beta1`: 0.9
|
| 316 |
+
- `adam_beta2`: 0.999
|
| 317 |
+
- `adam_epsilon`: 1e-08
|
| 318 |
+
- `max_grad_norm`: 1
|
| 319 |
+
- `num_train_epochs`: 10
|
| 320 |
+
- `max_steps`: -1
|
| 321 |
+
- `lr_scheduler_type`: linear
|
| 322 |
+
- `lr_scheduler_kwargs`: {}
|
| 323 |
+
- `warmup_ratio`: 0.0
|
| 324 |
+
- `warmup_steps`: 0
|
| 325 |
+
- `log_level`: passive
|
| 326 |
+
- `log_level_replica`: warning
|
| 327 |
+
- `log_on_each_node`: True
|
| 328 |
+
- `logging_nan_inf_filter`: True
|
| 329 |
+
- `save_safetensors`: True
|
| 330 |
+
- `save_on_each_node`: False
|
| 331 |
+
- `save_only_model`: False
|
| 332 |
+
- `restore_callback_states_from_checkpoint`: False
|
| 333 |
+
- `no_cuda`: False
|
| 334 |
+
- `use_cpu`: False
|
| 335 |
+
- `use_mps_device`: False
|
| 336 |
+
- `seed`: 42
|
| 337 |
+
- `data_seed`: None
|
| 338 |
+
- `jit_mode_eval`: False
|
| 339 |
+
- `use_ipex`: False
|
| 340 |
+
- `bf16`: False
|
| 341 |
+
- `fp16`: False
|
| 342 |
+
- `fp16_opt_level`: O1
|
| 343 |
+
- `half_precision_backend`: auto
|
| 344 |
+
- `bf16_full_eval`: False
|
| 345 |
+
- `fp16_full_eval`: False
|
| 346 |
+
- `tf32`: None
|
| 347 |
+
- `local_rank`: 0
|
| 348 |
+
- `ddp_backend`: None
|
| 349 |
+
- `tpu_num_cores`: None
|
| 350 |
+
- `tpu_metrics_debug`: False
|
| 351 |
+
- `debug`: []
|
| 352 |
+
- `dataloader_drop_last`: False
|
| 353 |
+
- `dataloader_num_workers`: 0
|
| 354 |
+
- `dataloader_prefetch_factor`: None
|
| 355 |
+
- `past_index`: -1
|
| 356 |
+
- `disable_tqdm`: False
|
| 357 |
+
- `remove_unused_columns`: True
|
| 358 |
+
- `label_names`: None
|
| 359 |
+
- `load_best_model_at_end`: False
|
| 360 |
+
- `ignore_data_skip`: False
|
| 361 |
+
- `fsdp`: []
|
| 362 |
+
- `fsdp_min_num_params`: 0
|
| 363 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
| 364 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
| 365 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
| 366 |
+
- `deepspeed`: None
|
| 367 |
+
- `label_smoothing_factor`: 0.0
|
| 368 |
+
- `optim`: adamw_torch
|
| 369 |
+
- `optim_args`: None
|
| 370 |
+
- `adafactor`: False
|
| 371 |
+
- `group_by_length`: False
|
| 372 |
+
- `length_column_name`: length
|
| 373 |
+
- `ddp_find_unused_parameters`: None
|
| 374 |
+
- `ddp_bucket_cap_mb`: None
|
| 375 |
+
- `ddp_broadcast_buffers`: False
|
| 376 |
+
- `dataloader_pin_memory`: True
|
| 377 |
+
- `dataloader_persistent_workers`: False
|
| 378 |
+
- `skip_memory_metrics`: True
|
| 379 |
+
- `use_legacy_prediction_loop`: False
|
| 380 |
+
- `push_to_hub`: False
|
| 381 |
+
- `resume_from_checkpoint`: None
|
| 382 |
+
- `hub_model_id`: None
|
| 383 |
+
- `hub_strategy`: every_save
|
| 384 |
+
- `hub_private_repo`: None
|
| 385 |
+
- `hub_always_push`: False
|
| 386 |
+
- `gradient_checkpointing`: False
|
| 387 |
+
- `gradient_checkpointing_kwargs`: None
|
| 388 |
+
- `include_inputs_for_metrics`: False
|
| 389 |
+
- `include_for_metrics`: []
|
| 390 |
+
- `eval_do_concat_batches`: True
|
| 391 |
+
- `fp16_backend`: auto
|
| 392 |
+
- `push_to_hub_model_id`: None
|
| 393 |
+
- `push_to_hub_organization`: None
|
| 394 |
+
- `mp_parameters`:
|
| 395 |
+
- `auto_find_batch_size`: False
|
| 396 |
+
- `full_determinism`: False
|
| 397 |
+
- `torchdynamo`: None
|
| 398 |
+
- `ray_scope`: last
|
| 399 |
+
- `ddp_timeout`: 1800
|
| 400 |
+
- `torch_compile`: False
|
| 401 |
+
- `torch_compile_backend`: None
|
| 402 |
+
- `torch_compile_mode`: None
|
| 403 |
+
- `dispatch_batches`: None
|
| 404 |
+
- `split_batches`: None
|
| 405 |
+
- `include_tokens_per_second`: False
|
| 406 |
+
- `include_num_input_tokens_seen`: False
|
| 407 |
+
- `neftune_noise_alpha`: None
|
| 408 |
+
- `optim_target_modules`: None
|
| 409 |
+
- `batch_eval_metrics`: False
|
| 410 |
+
- `eval_on_start`: False
|
| 411 |
+
- `use_liger_kernel`: False
|
| 412 |
+
- `eval_use_gather_object`: False
|
| 413 |
+
- `average_tokens_across_devices`: False
|
| 414 |
+
- `prompts`: None
|
| 415 |
+
- `batch_sampler`: batch_sampler
|
| 416 |
+
- `multi_dataset_batch_sampler`: round_robin
|
| 417 |
+
|
| 418 |
+
</details>
|
| 419 |
+
|
| 420 |
+
### Training Logs
|
| 421 |
+
| Epoch | Step | Training Loss | test-eval_cosine_ndcg@10 |
|
| 422 |
+
|:------:|:----:|:-------------:|:------------------------:|
|
| 423 |
+
| 1.0 | 104 | - | 0.9079 |
|
| 424 |
+
| 2.0 | 208 | - | 0.9334 |
|
| 425 |
+
| 3.0 | 312 | - | 0.9448 |
|
| 426 |
+
| 4.0 | 416 | - | 0.9447 |
|
| 427 |
+
| 4.8077 | 500 | 0.1486 | 0.9529 |
|
| 428 |
+
| 5.0 | 520 | - | 0.9543 |
|
| 429 |
+
| 6.0 | 624 | - | 0.9540 |
|
| 430 |
+
| 7.0 | 728 | - | 0.9560 |
|
| 431 |
+
| 8.0 | 832 | - | 0.9561 |
|
| 432 |
+
| 9.0 | 936 | - | 0.9560 |
|
| 433 |
+
| 9.6154 | 1000 | 0.1024 | 0.9600 |
|
| 434 |
+
|
| 435 |
+
|
| 436 |
+
### Framework Versions
|
| 437 |
+
- Python: 3.12.5
|
| 438 |
+
- Sentence Transformers: 3.4.1
|
| 439 |
+
- Transformers: 4.49.0
|
| 440 |
+
- PyTorch: 2.6.0
|
| 441 |
+
- Accelerate: 1.5.2
|
| 442 |
+
- Datasets: 3.4.1
|
| 443 |
+
- Tokenizers: 0.21.1
|
| 444 |
+
|
| 445 |
+
## Citation
|
| 446 |
+
|
| 447 |
+
### BibTeX
|
| 448 |
+
|
| 449 |
+
#### Sentence Transformers
|
| 450 |
+
```bibtex
|
| 451 |
+
@inproceedings{reimers-2019-sentence-bert,
|
| 452 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
| 453 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
| 454 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
| 455 |
+
month = "11",
|
| 456 |
+
year = "2019",
|
| 457 |
+
publisher = "Association for Computational Linguistics",
|
| 458 |
+
url = "https://arxiv.org/abs/1908.10084",
|
| 459 |
+
}
|
| 460 |
+
```
|
| 461 |
+
|
| 462 |
+
#### MultipleNegativesRankingLoss
|
| 463 |
+
```bibtex
|
| 464 |
+
@misc{henderson2017efficient,
|
| 465 |
+
title={Efficient Natural Language Response Suggestion for Smart Reply},
|
| 466 |
+
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},
|
| 467 |
+
year={2017},
|
| 468 |
+
eprint={1705.00652},
|
| 469 |
+
archivePrefix={arXiv},
|
| 470 |
+
primaryClass={cs.CL}
|
| 471 |
+
}
|
| 472 |
+
```
|
| 473 |
+
|
| 474 |
+
<!--
|
| 475 |
+
## Glossary
|
| 476 |
+
|
| 477 |
+
*Clearly define terms in order to be accessible across audiences.*
|
| 478 |
+
-->
|
| 479 |
+
|
| 480 |
+
<!--
|
| 481 |
+
## Model Card Authors
|
| 482 |
+
|
| 483 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
| 484 |
+
-->
|
| 485 |
+
|
| 486 |
+
<!--
|
| 487 |
+
## Model Card Contact
|
| 488 |
+
|
| 489 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
| 490 |
+
-->
|
config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "sentence-transformers/all-mpnet-base-v2",
|
| 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": "4.49.0",
|
| 23 |
+
"vocab_size": 30527
|
| 24 |
+
}
|
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 |
+
1.0,104,0.8072289156626506,0.9457831325301205,0.9759036144578314,0.9939759036144579,0.8072289156626506,0.8072289156626506,0.3152610441767068,0.9457831325301205,0.1951807228915662,0.9759036144578314,0.09939759036144578,0.9939759036144579,0.8794499426276531,0.9079390457506715,0.8798588179479393
|
| 3 |
+
2.0,208,0.8493975903614458,0.9728915662650602,0.9939759036144579,1.0,0.8493975903614458,0.8493975903614458,0.3242971887550201,0.9728915662650602,0.19879518072289157,0.9939759036144579,0.09999999999999999,1.0,0.9109772423025432,0.9333757438019133,0.9109772423025435
|
| 4 |
+
3.0,312,0.8704819277108434,0.9819277108433735,1.0,1.0,0.8704819277108434,0.8704819277108434,0.3273092369477911,0.9819277108433735,0.19999999999999998,1.0,0.09999999999999999,1.0,0.9259036144578312,0.9447664004420586,0.9259036144578312
|
| 5 |
+
4.0,416,0.8674698795180723,0.9879518072289156,1.0,1.0,0.8674698795180723,0.8674698795180723,0.3293172690763052,0.9879518072289156,0.19999999999999998,1.0,0.09999999999999999,1.0,0.9257530120481927,0.9447290883749765,0.9257530120481928
|
| 6 |
+
5.0,520,0.8855421686746988,0.9969879518072289,1.0,1.0,0.8855421686746988,0.8855421686746988,0.33232931726907633,0.9969879518072289,0.19999999999999998,1.0,0.09999999999999999,1.0,0.9383534136546182,0.9542612813686092,0.9383534136546183
|
| 7 |
+
6.0,624,0.8855421686746988,0.9969879518072289,1.0,1.0,0.8855421686746988,0.8855421686746988,0.3323293172690763,0.9969879518072289,0.19999999999999998,1.0,0.09999999999999999,1.0,0.9380020080321282,0.953998913890499,0.9380020080321284
|
| 8 |
+
7.0,728,0.8855421686746988,0.9969879518072289,1.0,1.0,0.8855421686746988,0.8855421686746988,0.33232931726907633,0.9969879518072289,0.19999999999999998,1.0,0.09999999999999999,1.0,0.9405120481927709,0.9559707475286235,0.9405120481927711
|
| 9 |
+
8.0,832,0.8885542168674698,0.9939759036144579,1.0,1.0,0.8885542168674698,0.8885542168674698,0.3313253012048193,0.9939759036144579,0.19999999999999998,1.0,0.09999999999999999,1.0,0.9407630522088352,0.9560848658941624,0.9407630522088353
|
| 10 |
+
9.0,936,0.891566265060241,0.9879518072289156,1.0,1.0,0.891566265060241,0.891566265060241,0.3293172690763052,0.9879518072289156,0.19999999999999998,1.0,0.09999999999999999,1.0,0.9407630522088353,0.95599017871173,0.9407630522088355
|
| 11 |
+
10.0,1040,0.8975903614457831,0.9969879518072289,1.0,1.0,0.8975903614457831,0.8975903614457831,0.33232931726907633,0.9969879518072289,0.19999999999999998,1.0,0.09999999999999999,1.0,0.9460341365461847,0.9600230102760412,0.9460341365461847
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d8d1fe8d418486187fcad32d7b2ad0e4a2d3688fe8552a85b65adf4808e0eb9
|
| 3 |
+
size 437967672
|
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": 384,
|
| 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 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"104": {
|
| 36 |
+
"content": "[UNK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"30526": {
|
| 44 |
+
"content": "<mask>",
|
| 45 |
+
"lstrip": true,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
}
|
| 51 |
+
},
|
| 52 |
+
"bos_token": "<s>",
|
| 53 |
+
"clean_up_tokenization_spaces": false,
|
| 54 |
+
"cls_token": "<s>",
|
| 55 |
+
"do_lower_case": true,
|
| 56 |
+
"eos_token": "</s>",
|
| 57 |
+
"extra_special_tokens": {},
|
| 58 |
+
"mask_token": "<mask>",
|
| 59 |
+
"max_length": 128,
|
| 60 |
+
"model_max_length": 384,
|
| 61 |
+
"pad_to_multiple_of": null,
|
| 62 |
+
"pad_token": "<pad>",
|
| 63 |
+
"pad_token_type_id": 0,
|
| 64 |
+
"padding_side": "right",
|
| 65 |
+
"sep_token": "</s>",
|
| 66 |
+
"stride": 0,
|
| 67 |
+
"strip_accents": null,
|
| 68 |
+
"tokenize_chinese_chars": true,
|
| 69 |
+
"tokenizer_class": "MPNetTokenizer",
|
| 70 |
+
"truncation_side": "right",
|
| 71 |
+
"truncation_strategy": "longest_first",
|
| 72 |
+
"unk_token": "[UNK]"
|
| 73 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|