Upload retrain embedding model
Browse files- 1_Pooling/config.json +10 -0
- README.md +577 -0
- config.json +30 -0
- config_sentence_transformers.json +14 -0
- model.safetensors +3 -0
- modules.json +20 -0
- sentence_bert_config.json +4 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
1_Pooling/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"word_embedding_dimension": 384,
|
| 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 +1,577 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
tags:
|
| 5 |
+
- sentence-transformers
|
| 6 |
+
- sentence-similarity
|
| 7 |
+
- feature-extraction
|
| 8 |
+
- dense
|
| 9 |
+
- generated_from_trainer
|
| 10 |
+
- dataset_size:556850
|
| 11 |
+
- loss:ContradictionMarginLoss
|
| 12 |
+
base_model: VinitT/Embeddings-Trivia
|
| 13 |
+
widget:
|
| 14 |
+
- source_sentence: Guy wearing sunglasses and blue shirt on skateboard in front of
|
| 15 |
+
a bright yellow building with palm trees.
|
| 16 |
+
sentences:
|
| 17 |
+
- Two people are standing by the street.
|
| 18 |
+
- A man rides a skateboard outside.
|
| 19 |
+
- The boys are inside laying down.
|
| 20 |
+
- source_sentence: In a park, a boy is bent to read the tree description, and a girl
|
| 21 |
+
is standing nearby waiting for him.
|
| 22 |
+
sentences:
|
| 23 |
+
- A boy and girl out in the park while looking at the scenery.
|
| 24 |
+
- Some girls are climbing.
|
| 25 |
+
- An illiterate boy standing up reading a tree description.
|
| 26 |
+
- source_sentence: A man in a blue shirt gesticulates as he speaks to a uniformed
|
| 27 |
+
official.
|
| 28 |
+
sentences:
|
| 29 |
+
- A man has a mouthfull of meatballs.
|
| 30 |
+
- A man is speaking with an official
|
| 31 |
+
- Women are working in a lab
|
| 32 |
+
- source_sentence: John left me, and a few minutes later I saw him from my window
|
| 33 |
+
walking slowly across the grass arm in arm with Cynthia Murdoch.
|
| 34 |
+
sentences:
|
| 35 |
+
- John left me to then walk with Cynthia Murdoch.
|
| 36 |
+
- A girl is wearing a crown while having a funny look on her face.
|
| 37 |
+
- John stayed and ignored Cynthia as she walked by.
|
| 38 |
+
- source_sentence: so he has overcome alcoholism at this point
|
| 39 |
+
sentences:
|
| 40 |
+
- A dog is holding a toy.
|
| 41 |
+
- He still is a heavy drinker and can't control it.
|
| 42 |
+
- He's gotten stronger and has overcome alcoholism.
|
| 43 |
+
datasets:
|
| 44 |
+
- sentence-transformers/all-nli
|
| 45 |
+
pipeline_tag: sentence-similarity
|
| 46 |
+
library_name: sentence-transformers
|
| 47 |
+
metrics:
|
| 48 |
+
- cosine_accuracy
|
| 49 |
+
model-index:
|
| 50 |
+
- name: SentenceTransformer based on VinitT/Embeddings-Trivia
|
| 51 |
+
results:
|
| 52 |
+
- task:
|
| 53 |
+
type: triplet
|
| 54 |
+
name: Triplet
|
| 55 |
+
dataset:
|
| 56 |
+
name: contra eval
|
| 57 |
+
type: contra_eval
|
| 58 |
+
metrics:
|
| 59 |
+
- type: cosine_accuracy
|
| 60 |
+
value: 0.949999988079071
|
| 61 |
+
name: Cosine Accuracy
|
| 62 |
+
---
|
| 63 |
+
|
| 64 |
+
# SentenceTransformer based on VinitT/Embeddings-Trivia
|
| 65 |
+
|
| 66 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [VinitT/Embeddings-Trivia](https://huggingface.co/VinitT/Embeddings-Trivia) on the [all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) dataset. It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
|
| 67 |
+
|
| 68 |
+
## Model Details
|
| 69 |
+
|
| 70 |
+
### Model Description
|
| 71 |
+
- **Model Type:** Sentence Transformer
|
| 72 |
+
- **Base model:** [VinitT/Embeddings-Trivia](https://huggingface.co/VinitT/Embeddings-Trivia) <!-- at revision f1c49cbecdbb76b4efd6ea97c91600816de94bb3 -->
|
| 73 |
+
- **Maximum Sequence Length:** 256 tokens
|
| 74 |
+
- **Output Dimensionality:** 384 dimensions
|
| 75 |
+
- **Similarity Function:** Cosine Similarity
|
| 76 |
+
- **Training Dataset:**
|
| 77 |
+
- [all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli)
|
| 78 |
+
- **Language:** en
|
| 79 |
+
<!-- - **License:** Unknown -->
|
| 80 |
+
|
| 81 |
+
### Model Sources
|
| 82 |
+
|
| 83 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
| 84 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/sentence-transformers)
|
| 85 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
| 86 |
+
|
| 87 |
+
### Full Model Architecture
|
| 88 |
+
|
| 89 |
+
```
|
| 90 |
+
SentenceTransformer(
|
| 91 |
+
(0): Transformer({'max_seq_length': 256, 'do_lower_case': False, 'architecture': 'BertModel'})
|
| 92 |
+
(1): Pooling({'word_embedding_dimension': 384, '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})
|
| 93 |
+
(2): Normalize()
|
| 94 |
+
)
|
| 95 |
+
```
|
| 96 |
+
|
| 97 |
+
## Usage
|
| 98 |
+
|
| 99 |
+
### Direct Usage (Sentence Transformers)
|
| 100 |
+
|
| 101 |
+
First install the Sentence Transformers library:
|
| 102 |
+
|
| 103 |
+
```bash
|
| 104 |
+
pip install -U sentence-transformers
|
| 105 |
+
```
|
| 106 |
+
|
| 107 |
+
Then you can load this model and run inference.
|
| 108 |
+
```python
|
| 109 |
+
from sentence_transformers import SentenceTransformer
|
| 110 |
+
|
| 111 |
+
# Download from the 🤗 Hub
|
| 112 |
+
model = SentenceTransformer("sentence_transformers_model_id")
|
| 113 |
+
# Run inference
|
| 114 |
+
sentences = [
|
| 115 |
+
'so he has overcome alcoholism at this point',
|
| 116 |
+
"He's gotten stronger and has overcome alcoholism.",
|
| 117 |
+
"He still is a heavy drinker and can't control it.",
|
| 118 |
+
]
|
| 119 |
+
embeddings = model.encode(sentences)
|
| 120 |
+
print(embeddings.shape)
|
| 121 |
+
# [3, 384]
|
| 122 |
+
|
| 123 |
+
# Get the similarity scores for the embeddings
|
| 124 |
+
similarities = model.similarity(embeddings, embeddings)
|
| 125 |
+
print(similarities)
|
| 126 |
+
# tensor([[1.0000, 0.7603, 0.0849],
|
| 127 |
+
# [0.7603, 1.0000, 0.0794],
|
| 128 |
+
# [0.0849, 0.0794, 1.0000]])
|
| 129 |
+
```
|
| 130 |
+
|
| 131 |
+
<!--
|
| 132 |
+
### Direct Usage (Transformers)
|
| 133 |
+
|
| 134 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
| 135 |
+
|
| 136 |
+
</details>
|
| 137 |
+
-->
|
| 138 |
+
|
| 139 |
+
<!--
|
| 140 |
+
### Downstream Usage (Sentence Transformers)
|
| 141 |
+
|
| 142 |
+
You can finetune this model on your own dataset.
|
| 143 |
+
|
| 144 |
+
<details><summary>Click to expand</summary>
|
| 145 |
+
|
| 146 |
+
</details>
|
| 147 |
+
-->
|
| 148 |
+
|
| 149 |
+
<!--
|
| 150 |
+
### Out-of-Scope Use
|
| 151 |
+
|
| 152 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
| 153 |
+
-->
|
| 154 |
+
|
| 155 |
+
## Evaluation
|
| 156 |
+
|
| 157 |
+
### Metrics
|
| 158 |
+
|
| 159 |
+
#### Triplet
|
| 160 |
+
|
| 161 |
+
* Dataset: `contra_eval`
|
| 162 |
+
* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
|
| 163 |
+
|
| 164 |
+
| Metric | Value |
|
| 165 |
+
|:--------------------|:---------|
|
| 166 |
+
| **cosine_accuracy** | **0.95** |
|
| 167 |
+
|
| 168 |
+
<!--
|
| 169 |
+
## Bias, Risks and Limitations
|
| 170 |
+
|
| 171 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
| 172 |
+
-->
|
| 173 |
+
|
| 174 |
+
<!--
|
| 175 |
+
### Recommendations
|
| 176 |
+
|
| 177 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
| 178 |
+
-->
|
| 179 |
+
|
| 180 |
+
## Training Details
|
| 181 |
+
|
| 182 |
+
### Training Dataset
|
| 183 |
+
|
| 184 |
+
#### all-nli
|
| 185 |
+
|
| 186 |
+
* Dataset: [all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) at [d482672](https://huggingface.co/datasets/sentence-transformers/all-nli/tree/d482672c8e74ce18da116f430137434ba2e52fab)
|
| 187 |
+
* Size: 556,850 training samples
|
| 188 |
+
* Columns: <code>anchor</code>, <code>positive</code>, <code>negative</code>, and <code>label</code>
|
| 189 |
+
* Approximate statistics based on the first 1000 samples:
|
| 190 |
+
| | anchor | positive | negative | label |
|
| 191 |
+
|:--------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:-----------------------------|
|
| 192 |
+
| type | string | string | string | int |
|
| 193 |
+
| details | <ul><li>min: 5 tokens</li><li>mean: 19.16 tokens</li><li>max: 194 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 11.86 tokens</li><li>max: 32 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 12.23 tokens</li><li>max: 37 tokens</li></ul> | <ul><li>1: 100.00%</li></ul> |
|
| 194 |
+
* Samples:
|
| 195 |
+
| anchor | positive | negative | label |
|
| 196 |
+
|:----------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------|:---------------------------------------------------------------------|:---------------|
|
| 197 |
+
| <code>a young girl wearing blue smiles.</code> | <code>A little girl wears blue.</code> | <code>A little girl frowns as she wears an ugly burlap sack.</code> | <code>1</code> |
|
| 198 |
+
| <code>An old man wearing a tan jacket and blue pants standing on a sidewalk with a small suitcase.</code> | <code>A man wearing a jacket and jeans holds a suitcase.</code> | <code>A young woman sits on a bench holding her purse.</code> | <code>1</code> |
|
| 199 |
+
| <code>The people are inside.</code> | <code>Two people are dancing by a red couch.</code> | <code>People walk up and down the steps in front of a church.</code> | <code>1</code> |
|
| 200 |
+
* Loss: <code>custom_loss.ContradictionMarginLoss</code> with these parameters:
|
| 201 |
+
```json
|
| 202 |
+
{
|
| 203 |
+
"margin_neutral": 0.2,
|
| 204 |
+
"margin_contradiction": 0.4
|
| 205 |
+
}
|
| 206 |
+
```
|
| 207 |
+
|
| 208 |
+
### Evaluation Dataset
|
| 209 |
+
|
| 210 |
+
#### all-nli
|
| 211 |
+
|
| 212 |
+
* Dataset: [all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) at [d482672](https://huggingface.co/datasets/sentence-transformers/all-nli/tree/d482672c8e74ce18da116f430137434ba2e52fab)
|
| 213 |
+
* Size: 1,000 evaluation samples
|
| 214 |
+
* Columns: <code>anchor</code>, <code>positive</code>, <code>negative</code>, and <code>label</code>
|
| 215 |
+
* Approximate statistics based on the first 1000 samples:
|
| 216 |
+
| | anchor | positive | negative | label |
|
| 217 |
+
|:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:-----------------------------|
|
| 218 |
+
| type | string | string | string | int |
|
| 219 |
+
| details | <ul><li>min: 5 tokens</li><li>mean: 18.67 tokens</li><li>max: 86 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 11.92 tokens</li><li>max: 41 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 12.13 tokens</li><li>max: 40 tokens</li></ul> | <ul><li>1: 100.00%</li></ul> |
|
| 220 |
+
* Samples:
|
| 221 |
+
| anchor | positive | negative | label |
|
| 222 |
+
|:------------------------------------------------------|:---------------------------------------------------------------------------|:----------------------------------------------------|:---------------|
|
| 223 |
+
| <code>An older man riding a bike.</code> | <code>An elderly man is biking</code> | <code>an old man is sleeping</code> | <code>1</code> |
|
| 224 |
+
| <code>The man is on a skateboard.</code> | <code>A shirtless man is doing a skateboard trick over a bike rail.</code> | <code>A man performs a bike trick on a ramp.</code> | <code>1</code> |
|
| 225 |
+
| <code>The Episcopalians are all going to hell.</code> | <code>The Episcopalians will not be going to heaven.</code> | <code>All Episcopalians will go to heaven.</code> | <code>1</code> |
|
| 226 |
+
* Loss: <code>custom_loss.ContradictionMarginLoss</code> with these parameters:
|
| 227 |
+
```json
|
| 228 |
+
{
|
| 229 |
+
"margin_neutral": 0.2,
|
| 230 |
+
"margin_contradiction": 0.4
|
| 231 |
+
}
|
| 232 |
+
```
|
| 233 |
+
|
| 234 |
+
### Training Hyperparameters
|
| 235 |
+
#### Non-Default Hyperparameters
|
| 236 |
+
|
| 237 |
+
- `eval_strategy`: steps
|
| 238 |
+
- `per_device_train_batch_size`: 64
|
| 239 |
+
- `per_device_eval_batch_size`: 64
|
| 240 |
+
- `learning_rate`: 2e-05
|
| 241 |
+
- `weight_decay`: 0.01
|
| 242 |
+
- `num_train_epochs`: 1
|
| 243 |
+
- `warmup_ratio`: 0.1
|
| 244 |
+
- `warmup_steps`: 0.1
|
| 245 |
+
- `fp16`: True
|
| 246 |
+
- `load_best_model_at_end`: True
|
| 247 |
+
|
| 248 |
+
#### All Hyperparameters
|
| 249 |
+
<details><summary>Click to expand</summary>
|
| 250 |
+
|
| 251 |
+
- `do_predict`: False
|
| 252 |
+
- `eval_strategy`: steps
|
| 253 |
+
- `prediction_loss_only`: True
|
| 254 |
+
- `per_device_train_batch_size`: 64
|
| 255 |
+
- `per_device_eval_batch_size`: 64
|
| 256 |
+
- `gradient_accumulation_steps`: 1
|
| 257 |
+
- `eval_accumulation_steps`: None
|
| 258 |
+
- `torch_empty_cache_steps`: None
|
| 259 |
+
- `learning_rate`: 2e-05
|
| 260 |
+
- `weight_decay`: 0.01
|
| 261 |
+
- `adam_beta1`: 0.9
|
| 262 |
+
- `adam_beta2`: 0.999
|
| 263 |
+
- `adam_epsilon`: 1e-08
|
| 264 |
+
- `max_grad_norm`: 1.0
|
| 265 |
+
- `num_train_epochs`: 1
|
| 266 |
+
- `max_steps`: -1
|
| 267 |
+
- `lr_scheduler_type`: linear
|
| 268 |
+
- `lr_scheduler_kwargs`: None
|
| 269 |
+
- `warmup_ratio`: 0.1
|
| 270 |
+
- `warmup_steps`: 0.1
|
| 271 |
+
- `log_level`: passive
|
| 272 |
+
- `log_level_replica`: warning
|
| 273 |
+
- `log_on_each_node`: True
|
| 274 |
+
- `logging_nan_inf_filter`: True
|
| 275 |
+
- `enable_jit_checkpoint`: False
|
| 276 |
+
- `save_on_each_node`: False
|
| 277 |
+
- `save_only_model`: False
|
| 278 |
+
- `restore_callback_states_from_checkpoint`: False
|
| 279 |
+
- `use_cpu`: False
|
| 280 |
+
- `seed`: 42
|
| 281 |
+
- `data_seed`: None
|
| 282 |
+
- `bf16`: False
|
| 283 |
+
- `fp16`: True
|
| 284 |
+
- `bf16_full_eval`: False
|
| 285 |
+
- `fp16_full_eval`: False
|
| 286 |
+
- `tf32`: None
|
| 287 |
+
- `local_rank`: -1
|
| 288 |
+
- `ddp_backend`: None
|
| 289 |
+
- `debug`: []
|
| 290 |
+
- `dataloader_drop_last`: False
|
| 291 |
+
- `dataloader_num_workers`: 0
|
| 292 |
+
- `dataloader_prefetch_factor`: None
|
| 293 |
+
- `disable_tqdm`: False
|
| 294 |
+
- `remove_unused_columns`: True
|
| 295 |
+
- `label_names`: None
|
| 296 |
+
- `load_best_model_at_end`: True
|
| 297 |
+
- `ignore_data_skip`: False
|
| 298 |
+
- `fsdp`: []
|
| 299 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
| 300 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
| 301 |
+
- `parallelism_config`: None
|
| 302 |
+
- `deepspeed`: None
|
| 303 |
+
- `label_smoothing_factor`: 0.0
|
| 304 |
+
- `optim`: adamw_torch_fused
|
| 305 |
+
- `optim_args`: None
|
| 306 |
+
- `group_by_length`: False
|
| 307 |
+
- `length_column_name`: length
|
| 308 |
+
- `project`: huggingface
|
| 309 |
+
- `trackio_space_id`: trackio
|
| 310 |
+
- `ddp_find_unused_parameters`: None
|
| 311 |
+
- `ddp_bucket_cap_mb`: None
|
| 312 |
+
- `ddp_broadcast_buffers`: False
|
| 313 |
+
- `dataloader_pin_memory`: True
|
| 314 |
+
- `dataloader_persistent_workers`: False
|
| 315 |
+
- `skip_memory_metrics`: True
|
| 316 |
+
- `push_to_hub`: False
|
| 317 |
+
- `resume_from_checkpoint`: None
|
| 318 |
+
- `hub_model_id`: None
|
| 319 |
+
- `hub_strategy`: every_save
|
| 320 |
+
- `hub_private_repo`: None
|
| 321 |
+
- `hub_always_push`: False
|
| 322 |
+
- `hub_revision`: None
|
| 323 |
+
- `gradient_checkpointing`: False
|
| 324 |
+
- `gradient_checkpointing_kwargs`: None
|
| 325 |
+
- `include_for_metrics`: []
|
| 326 |
+
- `eval_do_concat_batches`: True
|
| 327 |
+
- `auto_find_batch_size`: False
|
| 328 |
+
- `full_determinism`: False
|
| 329 |
+
- `ddp_timeout`: 1800
|
| 330 |
+
- `torch_compile`: False
|
| 331 |
+
- `torch_compile_backend`: None
|
| 332 |
+
- `torch_compile_mode`: None
|
| 333 |
+
- `include_num_input_tokens_seen`: no
|
| 334 |
+
- `neftune_noise_alpha`: None
|
| 335 |
+
- `optim_target_modules`: None
|
| 336 |
+
- `batch_eval_metrics`: False
|
| 337 |
+
- `eval_on_start`: False
|
| 338 |
+
- `use_liger_kernel`: False
|
| 339 |
+
- `liger_kernel_config`: None
|
| 340 |
+
- `eval_use_gather_object`: False
|
| 341 |
+
- `average_tokens_across_devices`: True
|
| 342 |
+
- `use_cache`: False
|
| 343 |
+
- `prompts`: None
|
| 344 |
+
- `batch_sampler`: batch_sampler
|
| 345 |
+
- `multi_dataset_batch_sampler`: proportional
|
| 346 |
+
- `router_mapping`: {}
|
| 347 |
+
- `learning_rate_mapping`: {}
|
| 348 |
+
|
| 349 |
+
</details>
|
| 350 |
+
|
| 351 |
+
### Training Logs
|
| 352 |
+
<details><summary>Click to expand</summary>
|
| 353 |
+
|
| 354 |
+
| Epoch | Step | Training Loss | Validation Loss | contra_eval_cosine_accuracy |
|
| 355 |
+
|:---------:|:--------:|:-------------:|:---------------:|:---------------------------:|
|
| 356 |
+
| 0.0001 | 1 | 0.2363 | - | - |
|
| 357 |
+
| 0.0057 | 50 | 0.1877 | - | - |
|
| 358 |
+
| 0.0115 | 100 | 0.1786 | - | - |
|
| 359 |
+
| 0.0172 | 150 | 0.1672 | - | - |
|
| 360 |
+
| 0.0230 | 200 | 0.1529 | - | - |
|
| 361 |
+
| 0.0287 | 250 | 0.1392 | - | - |
|
| 362 |
+
| 0.0345 | 300 | 0.1278 | - | - |
|
| 363 |
+
| 0.0402 | 350 | 0.1233 | - | - |
|
| 364 |
+
| 0.0460 | 400 | 0.1157 | - | - |
|
| 365 |
+
| 0.0517 | 450 | 0.1116 | - | - |
|
| 366 |
+
| 0.0575 | 500 | 0.1063 | 0.0983 | 0.9260 |
|
| 367 |
+
| 0.0632 | 550 | 0.1087 | - | - |
|
| 368 |
+
| 0.0690 | 600 | 0.1016 | - | - |
|
| 369 |
+
| 0.0747 | 650 | 0.1026 | - | - |
|
| 370 |
+
| 0.0805 | 700 | 0.0967 | - | - |
|
| 371 |
+
| 0.0862 | 750 | 0.0990 | - | - |
|
| 372 |
+
| 0.0919 | 800 | 0.0925 | - | - |
|
| 373 |
+
| 0.0977 | 850 | 0.0965 | - | - |
|
| 374 |
+
| 0.1034 | 900 | 0.0981 | - | - |
|
| 375 |
+
| 0.1092 | 950 | 0.0881 | - | - |
|
| 376 |
+
| 0.1149 | 1000 | 0.0920 | 0.0829 | 0.9410 |
|
| 377 |
+
| 0.1207 | 1050 | 0.0882 | - | - |
|
| 378 |
+
| 0.1264 | 1100 | 0.0839 | - | - |
|
| 379 |
+
| 0.1322 | 1150 | 0.0896 | - | - |
|
| 380 |
+
| 0.1379 | 1200 | 0.0858 | - | - |
|
| 381 |
+
| 0.1437 | 1250 | 0.0878 | - | - |
|
| 382 |
+
| 0.1494 | 1300 | 0.0857 | - | - |
|
| 383 |
+
| 0.1552 | 1350 | 0.0902 | - | - |
|
| 384 |
+
| 0.1609 | 1400 | 0.0793 | - | - |
|
| 385 |
+
| 0.1666 | 1450 | 0.0830 | - | - |
|
| 386 |
+
| 0.1724 | 1500 | 0.0827 | 0.0788 | 0.9380 |
|
| 387 |
+
| 0.1781 | 1550 | 0.0789 | - | - |
|
| 388 |
+
| 0.1839 | 1600 | 0.0834 | - | - |
|
| 389 |
+
| 0.1896 | 1650 | 0.0805 | - | - |
|
| 390 |
+
| 0.1954 | 1700 | 0.0795 | - | - |
|
| 391 |
+
| 0.2011 | 1750 | 0.0846 | - | - |
|
| 392 |
+
| 0.2069 | 1800 | 0.0822 | - | - |
|
| 393 |
+
| 0.2126 | 1850 | 0.0858 | - | - |
|
| 394 |
+
| 0.2184 | 1900 | 0.0785 | - | - |
|
| 395 |
+
| 0.2241 | 1950 | 0.0777 | - | - |
|
| 396 |
+
| 0.2299 | 2000 | 0.0746 | 0.0721 | 0.9460 |
|
| 397 |
+
| 0.2356 | 2050 | 0.0798 | - | - |
|
| 398 |
+
| 0.2414 | 2100 | 0.0798 | - | - |
|
| 399 |
+
| 0.2471 | 2150 | 0.0794 | - | - |
|
| 400 |
+
| 0.2528 | 2200 | 0.0769 | - | - |
|
| 401 |
+
| 0.2586 | 2250 | 0.0805 | - | - |
|
| 402 |
+
| 0.2643 | 2300 | 0.0782 | - | - |
|
| 403 |
+
| 0.2701 | 2350 | 0.0776 | - | - |
|
| 404 |
+
| 0.2758 | 2400 | 0.0776 | - | - |
|
| 405 |
+
| 0.2816 | 2450 | 0.0733 | - | - |
|
| 406 |
+
| 0.2873 | 2500 | 0.0750 | 0.0718 | 0.9440 |
|
| 407 |
+
| 0.2931 | 2550 | 0.0764 | - | - |
|
| 408 |
+
| 0.2988 | 2600 | 0.0775 | - | - |
|
| 409 |
+
| 0.3046 | 2650 | 0.0767 | - | - |
|
| 410 |
+
| 0.3103 | 2700 | 0.0766 | - | - |
|
| 411 |
+
| 0.3161 | 2750 | 0.0755 | - | - |
|
| 412 |
+
| 0.3218 | 2800 | 0.0752 | - | - |
|
| 413 |
+
| 0.3275 | 2850 | 0.0717 | - | - |
|
| 414 |
+
| 0.3333 | 2900 | 0.0714 | - | - |
|
| 415 |
+
| 0.3390 | 2950 | 0.0726 | - | - |
|
| 416 |
+
| 0.3448 | 3000 | 0.0751 | 0.0695 | 0.9470 |
|
| 417 |
+
| 0.3505 | 3050 | 0.0730 | - | - |
|
| 418 |
+
| 0.3563 | 3100 | 0.0733 | - | - |
|
| 419 |
+
| 0.3620 | 3150 | 0.0738 | - | - |
|
| 420 |
+
| 0.3678 | 3200 | 0.0701 | - | - |
|
| 421 |
+
| 0.3735 | 3250 | 0.0723 | - | - |
|
| 422 |
+
| 0.3793 | 3300 | 0.0759 | - | - |
|
| 423 |
+
| 0.3850 | 3350 | 0.0675 | - | - |
|
| 424 |
+
| 0.3908 | 3400 | 0.0696 | - | - |
|
| 425 |
+
| 0.3965 | 3450 | 0.0707 | - | - |
|
| 426 |
+
| 0.4023 | 3500 | 0.0705 | 0.0669 | 0.9440 |
|
| 427 |
+
| 0.4080 | 3550 | 0.0702 | - | - |
|
| 428 |
+
| 0.4137 | 3600 | 0.0716 | - | - |
|
| 429 |
+
| 0.4195 | 3650 | 0.0697 | - | - |
|
| 430 |
+
| 0.4252 | 3700 | 0.0721 | - | - |
|
| 431 |
+
| 0.4310 | 3750 | 0.0723 | - | - |
|
| 432 |
+
| 0.4367 | 3800 | 0.0741 | - | - |
|
| 433 |
+
| 0.4425 | 3850 | 0.0702 | - | - |
|
| 434 |
+
| 0.4482 | 3900 | 0.0653 | - | - |
|
| 435 |
+
| 0.4540 | 3950 | 0.0704 | - | - |
|
| 436 |
+
| 0.4597 | 4000 | 0.0718 | 0.0652 | 0.9450 |
|
| 437 |
+
| 0.4655 | 4050 | 0.0683 | - | - |
|
| 438 |
+
| 0.4712 | 4100 | 0.0719 | - | - |
|
| 439 |
+
| 0.4770 | 4150 | 0.0674 | - | - |
|
| 440 |
+
| 0.4827 | 4200 | 0.0659 | - | - |
|
| 441 |
+
| 0.4884 | 4250 | 0.0735 | - | - |
|
| 442 |
+
| 0.4942 | 4300 | 0.0737 | - | - |
|
| 443 |
+
| 0.4999 | 4350 | 0.0707 | - | - |
|
| 444 |
+
| 0.5057 | 4400 | 0.0690 | - | - |
|
| 445 |
+
| 0.5114 | 4450 | 0.0707 | - | - |
|
| 446 |
+
| 0.5172 | 4500 | 0.0696 | 0.0637 | 0.9470 |
|
| 447 |
+
| 0.5229 | 4550 | 0.0686 | - | - |
|
| 448 |
+
| 0.5287 | 4600 | 0.0710 | - | - |
|
| 449 |
+
| 0.5344 | 4650 | 0.0681 | - | - |
|
| 450 |
+
| 0.5402 | 4700 | 0.0667 | - | - |
|
| 451 |
+
| 0.5459 | 4750 | 0.0673 | - | - |
|
| 452 |
+
| 0.5517 | 4800 | 0.0618 | - | - |
|
| 453 |
+
| 0.5574 | 4850 | 0.0715 | - | - |
|
| 454 |
+
| 0.5632 | 4900 | 0.0703 | - | - |
|
| 455 |
+
| 0.5689 | 4950 | 0.0675 | - | - |
|
| 456 |
+
| 0.5746 | 5000 | 0.0715 | 0.0638 | 0.9500 |
|
| 457 |
+
| 0.5804 | 5050 | 0.0681 | - | - |
|
| 458 |
+
| 0.5861 | 5100 | 0.0628 | - | - |
|
| 459 |
+
| 0.5919 | 5150 | 0.0654 | - | - |
|
| 460 |
+
| 0.5976 | 5200 | 0.0662 | - | - |
|
| 461 |
+
| 0.6034 | 5250 | 0.0626 | - | - |
|
| 462 |
+
| 0.6091 | 5300 | 0.0660 | - | - |
|
| 463 |
+
| 0.6149 | 5350 | 0.0652 | - | - |
|
| 464 |
+
| 0.6206 | 5400 | 0.0687 | - | - |
|
| 465 |
+
| 0.6264 | 5450 | 0.0677 | - | - |
|
| 466 |
+
| 0.6321 | 5500 | 0.0683 | 0.0631 | 0.9530 |
|
| 467 |
+
| 0.6379 | 5550 | 0.0666 | - | - |
|
| 468 |
+
| 0.6436 | 5600 | 0.0663 | - | - |
|
| 469 |
+
| 0.6494 | 5650 | 0.0637 | - | - |
|
| 470 |
+
| 0.6551 | 5700 | 0.0687 | - | - |
|
| 471 |
+
| 0.6608 | 5750 | 0.0620 | - | - |
|
| 472 |
+
| 0.6666 | 5800 | 0.0664 | - | - |
|
| 473 |
+
| 0.6723 | 5850 | 0.0666 | - | - |
|
| 474 |
+
| 0.6781 | 5900 | 0.0632 | - | - |
|
| 475 |
+
| 0.6838 | 5950 | 0.0676 | - | - |
|
| 476 |
+
| 0.6896 | 6000 | 0.0638 | 0.0634 | 0.9530 |
|
| 477 |
+
| 0.6953 | 6050 | 0.0655 | - | - |
|
| 478 |
+
| 0.7011 | 6100 | 0.0651 | - | - |
|
| 479 |
+
| 0.7068 | 6150 | 0.0675 | - | - |
|
| 480 |
+
| 0.7126 | 6200 | 0.0685 | - | - |
|
| 481 |
+
| 0.7183 | 6250 | 0.0647 | - | - |
|
| 482 |
+
| 0.7241 | 6300 | 0.0609 | - | - |
|
| 483 |
+
| 0.7298 | 6350 | 0.0643 | - | - |
|
| 484 |
+
| 0.7355 | 6400 | 0.0628 | - | - |
|
| 485 |
+
| 0.7413 | 6450 | 0.0627 | - | - |
|
| 486 |
+
| **0.747** | **6500** | **0.0639** | **0.0621** | **0.954** |
|
| 487 |
+
| 0.7528 | 6550 | 0.0658 | - | - |
|
| 488 |
+
| 0.7585 | 6600 | 0.0667 | - | - |
|
| 489 |
+
| 0.7643 | 6650 | 0.0632 | - | - |
|
| 490 |
+
| 0.7700 | 6700 | 0.0616 | - | - |
|
| 491 |
+
| 0.7758 | 6750 | 0.0666 | - | - |
|
| 492 |
+
| 0.7815 | 6800 | 0.0634 | - | - |
|
| 493 |
+
| 0.7873 | 6850 | 0.0647 | - | - |
|
| 494 |
+
| 0.7930 | 6900 | 0.0644 | - | - |
|
| 495 |
+
| 0.7988 | 6950 | 0.0617 | - | - |
|
| 496 |
+
| 0.8045 | 7000 | 0.0677 | 0.0626 | 0.9510 |
|
| 497 |
+
| 0.8103 | 7050 | 0.0616 | - | - |
|
| 498 |
+
| 0.8160 | 7100 | 0.0633 | - | - |
|
| 499 |
+
| 0.8217 | 7150 | 0.0645 | - | - |
|
| 500 |
+
| 0.8275 | 7200 | 0.0656 | - | - |
|
| 501 |
+
| 0.8332 | 7250 | 0.0597 | - | - |
|
| 502 |
+
| 0.8390 | 7300 | 0.0670 | - | - |
|
| 503 |
+
| 0.8447 | 7350 | 0.0638 | - | - |
|
| 504 |
+
| 0.8505 | 7400 | 0.0641 | - | - |
|
| 505 |
+
| 0.8562 | 7450 | 0.0660 | - | - |
|
| 506 |
+
| 0.8620 | 7500 | 0.0687 | 0.0618 | 0.9490 |
|
| 507 |
+
| 0.8677 | 7550 | 0.0654 | - | - |
|
| 508 |
+
| 0.8735 | 7600 | 0.0633 | - | - |
|
| 509 |
+
| 0.8792 | 7650 | 0.0660 | - | - |
|
| 510 |
+
| 0.8850 | 7700 | 0.0674 | - | - |
|
| 511 |
+
| 0.8907 | 7750 | 0.0681 | - | - |
|
| 512 |
+
| 0.8964 | 7800 | 0.0601 | - | - |
|
| 513 |
+
| 0.9022 | 7850 | 0.0612 | - | - |
|
| 514 |
+
| 0.9079 | 7900 | 0.0626 | - | - |
|
| 515 |
+
| 0.9137 | 7950 | 0.0641 | - | - |
|
| 516 |
+
| 0.9194 | 8000 | 0.0633 | 0.0619 | 0.9470 |
|
| 517 |
+
| 0.9252 | 8050 | 0.0637 | - | - |
|
| 518 |
+
| 0.9309 | 8100 | 0.0630 | - | - |
|
| 519 |
+
| 0.9367 | 8150 | 0.0646 | - | - |
|
| 520 |
+
| 0.9424 | 8200 | 0.0648 | - | - |
|
| 521 |
+
| 0.9482 | 8250 | 0.0647 | - | - |
|
| 522 |
+
| 0.9539 | 8300 | 0.0601 | - | - |
|
| 523 |
+
| 0.9597 | 8350 | 0.0600 | - | - |
|
| 524 |
+
| 0.9654 | 8400 | 0.0668 | - | - |
|
| 525 |
+
| 0.9712 | 8450 | 0.0640 | - | - |
|
| 526 |
+
| 0.9769 | 8500 | 0.0579 | 0.0618 | 0.9500 |
|
| 527 |
+
| 0.9826 | 8550 | 0.0645 | - | - |
|
| 528 |
+
| 0.9884 | 8600 | 0.0614 | - | - |
|
| 529 |
+
| 0.9941 | 8650 | 0.0642 | - | - |
|
| 530 |
+
| 0.9999 | 8700 | 0.0652 | - | - |
|
| 531 |
+
|
| 532 |
+
* The bold row denotes the saved checkpoint.
|
| 533 |
+
</details>
|
| 534 |
+
|
| 535 |
+
### Framework Versions
|
| 536 |
+
- Python: 3.12.12
|
| 537 |
+
- Sentence Transformers: 5.2.2
|
| 538 |
+
- Transformers: 5.0.0
|
| 539 |
+
- PyTorch: 2.9.0+cu128
|
| 540 |
+
- Accelerate: 1.12.0
|
| 541 |
+
- Datasets: 4.0.0
|
| 542 |
+
- Tokenizers: 0.22.2
|
| 543 |
+
|
| 544 |
+
## Citation
|
| 545 |
+
|
| 546 |
+
### BibTeX
|
| 547 |
+
|
| 548 |
+
#### Sentence Transformers
|
| 549 |
+
```bibtex
|
| 550 |
+
@inproceedings{reimers-2019-sentence-bert,
|
| 551 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
| 552 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
| 553 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
| 554 |
+
month = "11",
|
| 555 |
+
year = "2019",
|
| 556 |
+
publisher = "Association for Computational Linguistics",
|
| 557 |
+
url = "https://arxiv.org/abs/1908.10084",
|
| 558 |
+
}
|
| 559 |
+
```
|
| 560 |
+
|
| 561 |
+
<!--
|
| 562 |
+
## Glossary
|
| 563 |
+
|
| 564 |
+
*Clearly define terms in order to be accessible across audiences.*
|
| 565 |
+
-->
|
| 566 |
+
|
| 567 |
+
<!--
|
| 568 |
+
## Model Card Authors
|
| 569 |
+
|
| 570 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
| 571 |
+
-->
|
| 572 |
+
|
| 573 |
+
<!--
|
| 574 |
+
## Model Card Contact
|
| 575 |
+
|
| 576 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
| 577 |
+
-->
|
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_cross_attention": false,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertModel"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": null,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"eos_token_id": null,
|
| 11 |
+
"gradient_checkpointing": false,
|
| 12 |
+
"hidden_act": "gelu",
|
| 13 |
+
"hidden_dropout_prob": 0.1,
|
| 14 |
+
"hidden_size": 384,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 1536,
|
| 17 |
+
"is_decoder": false,
|
| 18 |
+
"layer_norm_eps": 1e-12,
|
| 19 |
+
"max_position_embeddings": 512,
|
| 20 |
+
"model_type": "bert",
|
| 21 |
+
"num_attention_heads": 12,
|
| 22 |
+
"num_hidden_layers": 6,
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"position_embedding_type": "absolute",
|
| 25 |
+
"tie_word_embeddings": true,
|
| 26 |
+
"transformers_version": "5.0.0",
|
| 27 |
+
"type_vocab_size": 2,
|
| 28 |
+
"use_cache": true,
|
| 29 |
+
"vocab_size": 30522
|
| 30 |
+
}
|
config_sentence_transformers.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"__version__": {
|
| 3 |
+
"sentence_transformers": "5.2.2",
|
| 4 |
+
"transformers": "5.0.0",
|
| 5 |
+
"pytorch": "2.9.0+cu128"
|
| 6 |
+
},
|
| 7 |
+
"model_type": "SentenceTransformer",
|
| 8 |
+
"prompts": {
|
| 9 |
+
"query": "",
|
| 10 |
+
"document": ""
|
| 11 |
+
},
|
| 12 |
+
"default_prompt_name": null,
|
| 13 |
+
"similarity_fn_name": "cosine"
|
| 14 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:01142cda08807a89c1ef4f32f31a2d6eb707e05c2ea160ebc9402023b54a16db
|
| 3 |
+
size 90864176
|
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": 256,
|
| 3 |
+
"do_lower_case": false
|
| 4 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_basic_tokenize": true,
|
| 5 |
+
"do_lower_case": true,
|
| 6 |
+
"is_local": false,
|
| 7 |
+
"mask_token": "[MASK]",
|
| 8 |
+
"model_max_length": 256,
|
| 9 |
+
"never_split": null,
|
| 10 |
+
"pad_token": "[PAD]",
|
| 11 |
+
"sep_token": "[SEP]",
|
| 12 |
+
"strip_accents": null,
|
| 13 |
+
"tokenize_chinese_chars": true,
|
| 14 |
+
"tokenizer_class": "BertTokenizer",
|
| 15 |
+
"unk_token": "[UNK]"
|
| 16 |
+
}
|