Push model using huggingface_hub.
Browse files- 1_Pooling/config.json +10 -0
- README.md +264 -0
- config.json +25 -0
- config_sentence_transformers.json +10 -0
- config_setfit.json +4 -0
- model.safetensors +3 -0
- model_head.pkl +3 -0
- modules.json +14 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -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 +1,264 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- setfit
|
| 4 |
+
- sentence-transformers
|
| 5 |
+
- text-classification
|
| 6 |
+
- generated_from_setfit_trainer
|
| 7 |
+
widget:
|
| 8 |
+
- text: Teemu Karhu menetkö noin vaan takuuseen, ettei sodan johdosta näin käy? Ite
|
| 9 |
+
en kyllä menis 100% sanomaan mitään mihin liittyy Putin ja Putinin sota
|
| 10 |
+
- text: Kohta on lisää lapsia sairaalassa koronan vuoksi ☹
|
| 11 |
+
- text: Pirjo Rajakangas pyöräily sekä kävely ovat hyvää liikuntaa
|
| 12 |
+
- text: Hanna-Leena Lahti Niin.. Nuo todelliset tartunyamäärät voivat olla ihan mitä
|
| 13 |
+
tahansa. Mihinkään rajoitustoimiin ei tarvitsisi ryhtyä. Ihmiset voivat itse pitää
|
| 14 |
+
huolta itsestää, ja valtion tehtävä on pitää huolta siitä että hoitokapasiteetti
|
| 15 |
+
riittää. Tällä hetkellä meillä ei ole mitään hätää. Koko Suomessa tehohoidossa
|
| 16 |
+
koronan vuoksi on noin 2p ihmistä. Tehohoitopaikkoja siis riittää vielä vaikka
|
| 17 |
+
ja kuinka jos tarvetta. Korostan, että edelleenkin ovat turvavälit, hyvä hygienia
|
| 18 |
+
ja turhien kontaktien välttäminen kaikkein tärkeintä. Mitään ei tarvitsisi rajoittaa,
|
| 19 |
+
jollei ihmiset olisi niin helvetin tyhmiä, että osaisivat ajatella ihan omilla
|
| 20 |
+
aivoillaan, eikä valtion tarvitsisi heitä opastaa kädestä pitäen kuten jotain
|
| 21 |
+
pieniä lapsia.
|
| 22 |
+
- text: Mika, hallituksella pitää kuitenkin olla jokin pohja johon perustavat päätöksensä.
|
| 23 |
+
Poikkeustilaa ei voi loputtomiin jatkaa vain mutulla, jolloin heidän on kuunneltava
|
| 24 |
+
aiheen ammattilaisia.
|
| 25 |
+
metrics:
|
| 26 |
+
- metric
|
| 27 |
+
pipeline_tag: text-classification
|
| 28 |
+
library_name: setfit
|
| 29 |
+
inference: true
|
| 30 |
+
base_model: TurkuNLP/bert-base-finnish-cased-v1
|
| 31 |
+
model-index:
|
| 32 |
+
- name: SetFit with TurkuNLP/bert-base-finnish-cased-v1
|
| 33 |
+
results:
|
| 34 |
+
- task:
|
| 35 |
+
type: text-classification
|
| 36 |
+
name: Text Classification
|
| 37 |
+
dataset:
|
| 38 |
+
name: Unknown
|
| 39 |
+
type: unknown
|
| 40 |
+
split: test
|
| 41 |
+
metrics:
|
| 42 |
+
- type: metric
|
| 43 |
+
value: 0.7905009479595114
|
| 44 |
+
name: Metric
|
| 45 |
+
---
|
| 46 |
+
|
| 47 |
+
# SetFit with TurkuNLP/bert-base-finnish-cased-v1
|
| 48 |
+
|
| 49 |
+
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [TurkuNLP/bert-base-finnish-cased-v1](https://huggingface.co/TurkuNLP/bert-base-finnish-cased-v1) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
|
| 50 |
+
|
| 51 |
+
The model has been trained using an efficient few-shot learning technique that involves:
|
| 52 |
+
|
| 53 |
+
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
|
| 54 |
+
2. Training a classification head with features from the fine-tuned Sentence Transformer.
|
| 55 |
+
|
| 56 |
+
## Model Details
|
| 57 |
+
|
| 58 |
+
### Model Description
|
| 59 |
+
- **Model Type:** SetFit
|
| 60 |
+
- **Sentence Transformer body:** [TurkuNLP/bert-base-finnish-cased-v1](https://huggingface.co/TurkuNLP/bert-base-finnish-cased-v1)
|
| 61 |
+
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
|
| 62 |
+
- **Maximum Sequence Length:** 512 tokens
|
| 63 |
+
- **Number of Classes:** 2 classes
|
| 64 |
+
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
|
| 65 |
+
<!-- - **Language:** Unknown -->
|
| 66 |
+
<!-- - **License:** Unknown -->
|
| 67 |
+
|
| 68 |
+
### Model Sources
|
| 69 |
+
|
| 70 |
+
- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
|
| 71 |
+
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
|
| 72 |
+
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
|
| 73 |
+
|
| 74 |
+
### Model Labels
|
| 75 |
+
| Label | Examples |
|
| 76 |
+
|:------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
| 77 |
+
| 0 | <ul><li>'Christoffer Högström miten luulet tilanteen parantuneen kun sairaala- ja tehohoito potilaiden määrä on vain kasvanut silloisesta?\nOlet niin totaalisen puusilmäinen ja hallirusvihan vallassa, että tätä on turha jatkaa pitemmälle. Pysy terveenä ja rauhallista joulua!'</li><li>'"Hylkiö" unionin toimesta johon ei kuulu.'</li><li>'Pirjo-Liisa Almonkari-Kuikka en nyt varsinaisesti pelkästään tuota aihetta tarkoittanutkaan. Sekin on kuitenkin vähintään kyseenalaista, koska kyseessä ei ole valmis tuote, vaan hätämyyntiluvalla käytössä oleva ruiske, ja sen seurauksena on niinikään perusoikeudellinen terveydenhuollon taso turvaamattomalla tasolla.'</li></ul> |
|
| 78 |
+
| 1 | <ul><li>'Niko Korpela perustuslakia ei ole rikottu niissä asioissa mitä convoypellet väitti, kaikki mitä kaverit väittää ei ole totta .'</li><li>'Mikään ei ole niin varmaa kuin epävarma. KUKAAN ei millään voi tietää mitä tapahtuu koronan tai ylipäätään minkään suhteen. Joka muuta väittää on typerys...'</li><li>'Wallenius, kaupunginvaltuutettu Ei tietenkään. Hyvinhän me voimme itsekin tuottaa maakaasua ja raakaöljyä. Eikös?'</li></ul> |
|
| 79 |
+
|
| 80 |
+
## Evaluation
|
| 81 |
+
|
| 82 |
+
### Metrics
|
| 83 |
+
| Label | Metric |
|
| 84 |
+
|:--------|:-------|
|
| 85 |
+
| **all** | 0.7905 |
|
| 86 |
+
|
| 87 |
+
## Uses
|
| 88 |
+
|
| 89 |
+
### Direct Use for Inference
|
| 90 |
+
|
| 91 |
+
First install the SetFit library:
|
| 92 |
+
|
| 93 |
+
```bash
|
| 94 |
+
pip install setfit
|
| 95 |
+
```
|
| 96 |
+
|
| 97 |
+
Then you can load this model and run inference.
|
| 98 |
+
|
| 99 |
+
```python
|
| 100 |
+
from setfit import SetFitModel
|
| 101 |
+
|
| 102 |
+
# Download from the 🤗 Hub
|
| 103 |
+
model = SetFitModel.from_pretrained("Finnish-actions/SetFit-FinBERT1-Avg-challenge")
|
| 104 |
+
# Run inference
|
| 105 |
+
preds = model("Kohta on lisää lapsia sairaalassa koronan vuoksi ☹")
|
| 106 |
+
```
|
| 107 |
+
|
| 108 |
+
<!--
|
| 109 |
+
### Downstream Use
|
| 110 |
+
|
| 111 |
+
*List how someone could finetune this model on their own dataset.*
|
| 112 |
+
-->
|
| 113 |
+
|
| 114 |
+
<!--
|
| 115 |
+
### Out-of-Scope Use
|
| 116 |
+
|
| 117 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
| 118 |
+
-->
|
| 119 |
+
|
| 120 |
+
<!--
|
| 121 |
+
## Bias, Risks and Limitations
|
| 122 |
+
|
| 123 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
| 124 |
+
-->
|
| 125 |
+
|
| 126 |
+
<!--
|
| 127 |
+
### Recommendations
|
| 128 |
+
|
| 129 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
| 130 |
+
-->
|
| 131 |
+
|
| 132 |
+
## Training Details
|
| 133 |
+
|
| 134 |
+
### Training Set Metrics
|
| 135 |
+
| Training set | Min | Median | Max |
|
| 136 |
+
|:-------------|:----|:--------|:----|
|
| 137 |
+
| Word count | 1 | 19.9323 | 213 |
|
| 138 |
+
|
| 139 |
+
| Label | Training Sample Count |
|
| 140 |
+
|:------|:----------------------|
|
| 141 |
+
| 0 | 754 |
|
| 142 |
+
| 1 | 88 |
|
| 143 |
+
|
| 144 |
+
### Training Hyperparameters
|
| 145 |
+
- batch_size: (16, 16)
|
| 146 |
+
- num_epochs: (4, 4)
|
| 147 |
+
- max_steps: -1
|
| 148 |
+
- sampling_strategy: oversampling
|
| 149 |
+
- num_iterations: 6
|
| 150 |
+
- body_learning_rate: (2e-05, 1e-05)
|
| 151 |
+
- head_learning_rate: 0.01
|
| 152 |
+
- loss: CosineSimilarityLoss
|
| 153 |
+
- distance_metric: cosine_distance
|
| 154 |
+
- margin: 0.25
|
| 155 |
+
- end_to_end: False
|
| 156 |
+
- use_amp: False
|
| 157 |
+
- warmup_proportion: 0.1
|
| 158 |
+
- l2_weight: 0.01
|
| 159 |
+
- seed: 42
|
| 160 |
+
- evaluation_strategy: epoch
|
| 161 |
+
- eval_max_steps: -1
|
| 162 |
+
- load_best_model_at_end: False
|
| 163 |
+
|
| 164 |
+
### Training Results
|
| 165 |
+
| Epoch | Step | Training Loss | Validation Loss |
|
| 166 |
+
|:------:|:----:|:-------------:|:---------------:|
|
| 167 |
+
| 0.0016 | 1 | 0.2574 | - |
|
| 168 |
+
| 0.0791 | 50 | 0.2818 | - |
|
| 169 |
+
| 0.1582 | 100 | 0.2458 | - |
|
| 170 |
+
| 0.2373 | 150 | 0.2051 | - |
|
| 171 |
+
| 0.3165 | 200 | 0.116 | - |
|
| 172 |
+
| 0.3956 | 250 | 0.0396 | - |
|
| 173 |
+
| 0.4747 | 300 | 0.0096 | - |
|
| 174 |
+
| 0.5538 | 350 | 0.0027 | - |
|
| 175 |
+
| 0.6329 | 400 | 0.0008 | - |
|
| 176 |
+
| 0.7120 | 450 | 0.0003 | - |
|
| 177 |
+
| 0.7911 | 500 | 0.0008 | - |
|
| 178 |
+
| 0.8703 | 550 | 0.0003 | - |
|
| 179 |
+
| 0.9494 | 600 | 0.0002 | - |
|
| 180 |
+
| 1.0 | 632 | - | 0.4312 |
|
| 181 |
+
| 1.0285 | 650 | 0.0001 | - |
|
| 182 |
+
| 1.1076 | 700 | 0.0001 | - |
|
| 183 |
+
| 1.1867 | 750 | 0.0001 | - |
|
| 184 |
+
| 1.2658 | 800 | 0.0001 | - |
|
| 185 |
+
| 1.3449 | 850 | 0.0001 | - |
|
| 186 |
+
| 1.4241 | 900 | 0.0001 | - |
|
| 187 |
+
| 1.5032 | 950 | 0.0001 | - |
|
| 188 |
+
| 1.5823 | 1000 | 0.0003 | - |
|
| 189 |
+
| 1.6614 | 1050 | 0.0001 | - |
|
| 190 |
+
| 1.7405 | 1100 | 0.0001 | - |
|
| 191 |
+
| 1.8196 | 1150 | 0.0001 | - |
|
| 192 |
+
| 1.8987 | 1200 | 0.0 | - |
|
| 193 |
+
| 1.9778 | 1250 | 0.0001 | - |
|
| 194 |
+
| 2.0 | 1264 | - | 0.4345 |
|
| 195 |
+
| 2.0570 | 1300 | 0.0 | - |
|
| 196 |
+
| 2.1361 | 1350 | 0.0 | - |
|
| 197 |
+
| 2.2152 | 1400 | 0.0 | - |
|
| 198 |
+
| 2.2943 | 1450 | 0.0 | - |
|
| 199 |
+
| 2.3734 | 1500 | 0.0 | - |
|
| 200 |
+
| 2.4525 | 1550 | 0.0 | - |
|
| 201 |
+
| 2.5316 | 1600 | 0.0 | - |
|
| 202 |
+
| 2.6108 | 1650 | 0.0 | - |
|
| 203 |
+
| 2.6899 | 1700 | 0.0001 | - |
|
| 204 |
+
| 2.7690 | 1750 | 0.0 | - |
|
| 205 |
+
| 2.8481 | 1800 | 0.0 | - |
|
| 206 |
+
| 2.9272 | 1850 | 0.0001 | - |
|
| 207 |
+
| 3.0 | 1896 | - | 0.4053 |
|
| 208 |
+
| 3.0063 | 1900 | 0.0003 | - |
|
| 209 |
+
| 3.0854 | 1950 | 0.0 | - |
|
| 210 |
+
| 3.1646 | 2000 | 0.0 | - |
|
| 211 |
+
| 3.2437 | 2050 | 0.0 | - |
|
| 212 |
+
| 3.3228 | 2100 | 0.0 | - |
|
| 213 |
+
| 3.4019 | 2150 | 0.0 | - |
|
| 214 |
+
| 3.4810 | 2200 | 0.0 | - |
|
| 215 |
+
| 3.5601 | 2250 | 0.0 | - |
|
| 216 |
+
| 3.6392 | 2300 | 0.0 | - |
|
| 217 |
+
| 3.7184 | 2350 | 0.0 | - |
|
| 218 |
+
| 3.7975 | 2400 | 0.0 | - |
|
| 219 |
+
| 3.8766 | 2450 | 0.0 | - |
|
| 220 |
+
| 3.9557 | 2500 | 0.0 | - |
|
| 221 |
+
| 4.0 | 2528 | - | 0.4416 |
|
| 222 |
+
|
| 223 |
+
### Framework Versions
|
| 224 |
+
- Python: 3.11.9
|
| 225 |
+
- SetFit: 1.1.3
|
| 226 |
+
- Sentence Transformers: 3.2.0
|
| 227 |
+
- Transformers: 4.44.0
|
| 228 |
+
- PyTorch: 2.4.0+cu124
|
| 229 |
+
- Datasets: 2.21.0
|
| 230 |
+
- Tokenizers: 0.19.1
|
| 231 |
+
|
| 232 |
+
## Citation
|
| 233 |
+
|
| 234 |
+
### BibTeX
|
| 235 |
+
```bibtex
|
| 236 |
+
@article{https://doi.org/10.48550/arxiv.2209.11055,
|
| 237 |
+
doi = {10.48550/ARXIV.2209.11055},
|
| 238 |
+
url = {https://arxiv.org/abs/2209.11055},
|
| 239 |
+
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
|
| 240 |
+
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
|
| 241 |
+
title = {Efficient Few-Shot Learning Without Prompts},
|
| 242 |
+
publisher = {arXiv},
|
| 243 |
+
year = {2022},
|
| 244 |
+
copyright = {Creative Commons Attribution 4.0 International}
|
| 245 |
+
}
|
| 246 |
+
```
|
| 247 |
+
|
| 248 |
+
<!--
|
| 249 |
+
## Glossary
|
| 250 |
+
|
| 251 |
+
*Clearly define terms in order to be accessible across audiences.*
|
| 252 |
+
-->
|
| 253 |
+
|
| 254 |
+
<!--
|
| 255 |
+
## Model Card Authors
|
| 256 |
+
|
| 257 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
| 258 |
+
-->
|
| 259 |
+
|
| 260 |
+
<!--
|
| 261 |
+
## Model Card Contact
|
| 262 |
+
|
| 263 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
| 264 |
+
-->
|
config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "TurkuNLP/bert-base-finnish-cased-v1",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertModel"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 3072,
|
| 13 |
+
"layer_norm_eps": 1e-12,
|
| 14 |
+
"max_position_embeddings": 512,
|
| 15 |
+
"model_type": "bert",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 12,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"position_embedding_type": "absolute",
|
| 20 |
+
"torch_dtype": "float32",
|
| 21 |
+
"transformers_version": "4.44.0",
|
| 22 |
+
"type_vocab_size": 2,
|
| 23 |
+
"use_cache": true,
|
| 24 |
+
"vocab_size": 50105
|
| 25 |
+
}
|
config_sentence_transformers.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"__version__": {
|
| 3 |
+
"sentence_transformers": "3.2.0",
|
| 4 |
+
"transformers": "4.44.0",
|
| 5 |
+
"pytorch": "2.4.0+cu124"
|
| 6 |
+
},
|
| 7 |
+
"prompts": {},
|
| 8 |
+
"default_prompt_name": null,
|
| 9 |
+
"similarity_fn_name": null
|
| 10 |
+
}
|
config_setfit.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"normalize_embeddings": false,
|
| 3 |
+
"labels": null
|
| 4 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f51457a73ca7ff7a2e8a819ae744336d80f5e917e3c064b4edeb5475b3a05e4a
|
| 3 |
+
size 498110312
|
model_head.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d950e54928cb7ce04995e8b52c26b84956e0333334e460a6338418f7c08f78a4
|
| 3 |
+
size 7007
|
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 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"101": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"102": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"103": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"104": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": false,
|
| 47 |
+
"mask_token": "[MASK]",
|
| 48 |
+
"model_max_length": 512,
|
| 49 |
+
"pad_token": "[PAD]",
|
| 50 |
+
"sep_token": "[SEP]",
|
| 51 |
+
"strip_accents": null,
|
| 52 |
+
"tokenize_chinese_chars": true,
|
| 53 |
+
"tokenizer_class": "BertTokenizer",
|
| 54 |
+
"unk_token": "[UNK]"
|
| 55 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|