Add SetFit ABSA model
Browse files- .gitattributes +1 -0
- 1_Pooling/config.json +10 -0
- README.md +253 -0
- config.json +28 -0
- config_sentence_transformers.json +10 -0
- config_setfit.json +11 -0
- model.safetensors +3 -0
- model_head.pkl +3 -0
- modules.json +20 -0
- sentence_bert_config.json +4 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +3 -0
- tokenizer_config.json +62 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
1_Pooling/config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"word_embedding_dimension": 1024,
|
3 |
+
"pooling_mode_cls_token": true,
|
4 |
+
"pooling_mode_mean_tokens": false,
|
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 +1,253 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: setfit
|
3 |
+
tags:
|
4 |
+
- setfit
|
5 |
+
- absa
|
6 |
+
- sentence-transformers
|
7 |
+
- text-classification
|
8 |
+
- generated_from_setfit_trainer
|
9 |
+
metrics:
|
10 |
+
- accuracy
|
11 |
+
widget:
|
12 |
+
- text: genshin impact, grafik nya udah bagus:pengalaman yang aku rasakan saat main
|
13 |
+
genshin impact, grafik nya udah bagus, sesuai dengan ukurannya yang besar, tapi
|
14 |
+
ada hal yang nyeselin saat aku main genshin impact, ada bug layar hp aku suka
|
15 |
+
gerak gerak sendiri saat aku baru baru download genshin impact itu layarnya gak
|
16 |
+
gerak sendiri, pengalaman saya main genshin impact sekarang ini gak nyaman karena
|
17 |
+
ada bug layar gerak sendiri. mohon bantuannya cognnosphere pte. ltd.
|
18 |
+
- text: grafiknya juga keren karakternya cakep:gamenya sangat bagus sama grafiknya
|
19 |
+
juga keren karakternya cakep
|
20 |
+
- text: aja tidak ada fitur skip story apalagi:genshin impact game kikir saya sudah
|
21 |
+
main 3 tahun masih gitu2 aja hadiah ulang tahun sama imlek hadiahnya biasa2 aja
|
22 |
+
tidak ada fitur skip story apalagi story nya bikin ngantuk jadi makin boring main
|
23 |
+
ini, mc bisu kebanyakan paimon yang banyak bicaranya berisik lagi tuh
|
24 |
+
- text: ',mulai dari konten yang disajikan sampai:overall game nya bagus,mulai dari
|
25 |
+
konten yang disajikan sampai design karakter nya,namun yang disayangkan adalah
|
26 |
+
performa gameplay nya untuk hp kelas low end karena saya mengalami force close
|
27 |
+
setiap kali mulai selesai quest,jadi mohon agar developer nya memperhatikan masalah
|
28 |
+
ini'
|
29 |
+
- text: story mantul, map luas bgt,:game paling debes yg pernah gwe temuin ampe saat
|
30 |
+
ini. gameplay seru, story mantul, map luas bgt, grapik jangan di tanya salutlah
|
31 |
+
ama hoyoverse. coba klo hoyoverse lebih ngurusin ni game bakalan jadi lebih seru
|
32 |
+
lagi d
|
33 |
+
pipeline_tag: text-classification
|
34 |
+
inference: false
|
35 |
+
---
|
36 |
+
|
37 |
+
# SetFit Polarity Model
|
38 |
+
|
39 |
+
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Aspect Based Sentiment Analysis (ABSA). A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification. In particular, this model is in charge of classifying aspect polarities.
|
40 |
+
|
41 |
+
The model has been trained using an efficient few-shot learning technique that involves:
|
42 |
+
|
43 |
+
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
|
44 |
+
2. Training a classification head with features from the fine-tuned Sentence Transformer.
|
45 |
+
|
46 |
+
This model was trained within the context of a larger system for ABSA, which looks like so:
|
47 |
+
|
48 |
+
1. Use a spaCy model to select possible aspect span candidates.
|
49 |
+
2. Use a SetFit model to filter these possible aspect span candidates.
|
50 |
+
3. **Use this SetFit model to classify the filtered aspect span candidates.**
|
51 |
+
|
52 |
+
## Model Details
|
53 |
+
|
54 |
+
### Model Description
|
55 |
+
- **Model Type:** SetFit
|
56 |
+
<!-- - **Sentence Transformer:** [Unknown](https://huggingface.co/unknown) -->
|
57 |
+
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
|
58 |
+
- **spaCy Model:** id_core_news_trf
|
59 |
+
- **SetFitABSA Aspect Model:** [Funnyworld1412/ABSA_review_game_genshin-aspect](https://huggingface.co/Funnyworld1412/ABSA_review_game_genshin-aspect)
|
60 |
+
- **SetFitABSA Polarity Model:** [Funnyworld1412/ABSA_review_game_genshin-polarity](https://huggingface.co/Funnyworld1412/ABSA_review_game_genshin-polarity)
|
61 |
+
- **Maximum Sequence Length:** 8192 tokens
|
62 |
+
- **Number of Classes:** 2 classes
|
63 |
+
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
|
64 |
+
<!-- - **Language:** Unknown -->
|
65 |
+
<!-- - **License:** Unknown -->
|
66 |
+
|
67 |
+
### Model Sources
|
68 |
+
|
69 |
+
- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
|
70 |
+
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
|
71 |
+
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
|
72 |
+
|
73 |
+
### Model Labels
|
74 |
+
| Label | Examples |
|
75 |
+
|:---------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
76 |
+
| Negative | <ul><li>'kebanyakan npc teyvat story utama punya mc:saranku developer harus menciptakan sebuah story yang sangat menarik, agar tidak kehilangan para player karena masalahnya banyak player yg tidak bertahan lama karena repetitif dan monoton tiap update, size makin gede doang yg isinya cuma chest baru itupun sampah, puzzle yg makin lama makin rumit tapi chest nya sampah, story kebanyakan npc teyvat story utama punya mc dilupain gak difokusin , map kalo udah kosong ya nyampah bikin size gede doang. main 3 tahun rasanya monoton, perkembangan buruk'</li><li>'tolong ditambah lagi reward untuk gachanya,:tolong ditambah lagi reward untuk gachanya, untuk player lama kesulitan mendapatkan primo karena sudah tidak ada lagi quest dan eksplorasi juga sudah 100 . dasar developer kapitalis, game ini makin lama makin monoton dan tidak ramah untuk player lama yang kekurangan bahan untuk gacha karakter'</li><li>'aja... sampek event selesai primogemnya buat:cuman saran jangan terlalu pelit.. biar para player gak kabur sama game sebelah hadiah event quest di perbaiki.... udah nunggu event lama lama hadiah cuman gitu gitu aja... sampek event selesai primogemnya buat 10 pull gacha gak cukup.... tingakat kesulitan beda hadiah sama saja... lama lama yang main pada kabur kalok terlalu pelit.. dan 1 lagi jariang mohon di perbaiki untuk server indonya trimaksih'</li></ul> |
|
77 |
+
| Positive | <ul><li>'gameplay nya memang menarik:gameplay nya memang menarik tapi story questnya bikin boring setiap lagi menyelesaikan quest kepala saya selalu frustasi karna dialog yang gak ngotak panjangnya mana gak bisa di skip selain itu developer selalu pelit untuk memberikan hadiah,saya sudah tidak merasa senang lagi bermain game ini karna ke kikirannya,puzzle nya,dan questnya membuat otak saya pusing developer juga lama memberi respon saat ada bug harus tunggu viral dulu baru bug nya di benerin'</li><li>'mulai dari cerita story, sound effect:tolong jangan pelit lah hoyoverse sama pemain baru atau pemain yg lama yg main kembali karna pemain paling suka kalau banyak gratisan ntah itu artefak, primoge, character, atau pun item karna jujur saja sebagai pemain baru saya merasa kurang puas sama gamenya apalagi buat upgrade character itu harus kumpulan item yg kebanyakan susah didapat bagi pemain baru itu saya kekurangan dari game ini selebihnya bagus mulai dari cerita story, sound effect, maupun tampilan didalam game yg lumayan bagus'</li><li>'cerita story, sound effect, maupun tampilan:tolong jangan pelit lah hoyoverse sama pemain baru atau pemain yg lama yg main kembali karna pemain paling suka kalau banyak gratisan ntah itu artefak, primoge, character, atau pun item karna jujur saja sebagai pemain baru saya merasa kurang puas sama gamenya apalagi buat upgrade character itu harus kumpulan item yg kebanyakan susah didapat bagi pemain baru itu saya kekurangan dari game ini selebihnya bagus mulai dari cerita story, sound effect, maupun tampilan didalam game yg lumayan bagus'</li></ul> |
|
78 |
+
|
79 |
+
## Uses
|
80 |
+
|
81 |
+
### Direct Use for Inference
|
82 |
+
|
83 |
+
First install the SetFit library:
|
84 |
+
|
85 |
+
```bash
|
86 |
+
pip install setfit
|
87 |
+
```
|
88 |
+
|
89 |
+
Then you can load this model and run inference.
|
90 |
+
|
91 |
+
```python
|
92 |
+
from setfit import AbsaModel
|
93 |
+
|
94 |
+
# Download from the 🤗 Hub
|
95 |
+
model = AbsaModel.from_pretrained(
|
96 |
+
"Funnyworld1412/ABSA_review_game_genshin-aspect",
|
97 |
+
"Funnyworld1412/ABSA_review_game_genshin-polarity",
|
98 |
+
)
|
99 |
+
# Run inference
|
100 |
+
preds = model("The food was great, but the venue is just way too busy.")
|
101 |
+
```
|
102 |
+
|
103 |
+
<!--
|
104 |
+
### Downstream Use
|
105 |
+
|
106 |
+
*List how someone could finetune this model on their own dataset.*
|
107 |
+
-->
|
108 |
+
|
109 |
+
<!--
|
110 |
+
### Out-of-Scope Use
|
111 |
+
|
112 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
113 |
+
-->
|
114 |
+
|
115 |
+
<!--
|
116 |
+
## Bias, Risks and Limitations
|
117 |
+
|
118 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
119 |
+
-->
|
120 |
+
|
121 |
+
<!--
|
122 |
+
### Recommendations
|
123 |
+
|
124 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
125 |
+
-->
|
126 |
+
|
127 |
+
## Training Details
|
128 |
+
|
129 |
+
### Training Set Metrics
|
130 |
+
| Training set | Min | Median | Max |
|
131 |
+
|:-------------|:----|:--------|:----|
|
132 |
+
| Word count | 6 | 46.7275 | 98 |
|
133 |
+
|
134 |
+
| Label | Training Sample Count |
|
135 |
+
|:--------|:----------------------|
|
136 |
+
| konflik | 0 |
|
137 |
+
| negatif | 0 |
|
138 |
+
| netral | 0 |
|
139 |
+
| positif | 0 |
|
140 |
+
|
141 |
+
### Training Hyperparameters
|
142 |
+
- batch_size: (4, 4)
|
143 |
+
- num_epochs: (1, 1)
|
144 |
+
- max_steps: -1
|
145 |
+
- sampling_strategy: oversampling
|
146 |
+
- num_iterations: 10
|
147 |
+
- body_learning_rate: (2e-05, 1e-05)
|
148 |
+
- head_learning_rate: 0.01
|
149 |
+
- loss: CosineSimilarityLoss
|
150 |
+
- distance_metric: cosine_distance
|
151 |
+
- margin: 0.25
|
152 |
+
- end_to_end: False
|
153 |
+
- use_amp: False
|
154 |
+
- warmup_proportion: 0.1
|
155 |
+
- seed: 42
|
156 |
+
- eval_max_steps: -1
|
157 |
+
- load_best_model_at_end: False
|
158 |
+
|
159 |
+
### Training Results
|
160 |
+
| Epoch | Step | Training Loss | Validation Loss |
|
161 |
+
|:------:|:----:|:-------------:|:---------------:|
|
162 |
+
| 0.0004 | 1 | 0.2547 | - |
|
163 |
+
| 0.0210 | 50 | 0.2787 | - |
|
164 |
+
| 0.0419 | 100 | 0.002 | - |
|
165 |
+
| 0.0629 | 150 | 0.2062 | - |
|
166 |
+
| 0.0839 | 200 | 0.2148 | - |
|
167 |
+
| 0.1048 | 250 | 0.209 | - |
|
168 |
+
| 0.1258 | 300 | 0.1926 | - |
|
169 |
+
| 0.1468 | 350 | 0.2244 | - |
|
170 |
+
| 0.1677 | 400 | 0.0034 | - |
|
171 |
+
| 0.1887 | 450 | 0.2523 | - |
|
172 |
+
| 0.2096 | 500 | 0.0027 | - |
|
173 |
+
| 0.2306 | 550 | 0.001 | - |
|
174 |
+
| 0.2516 | 600 | 0.0016 | - |
|
175 |
+
| 0.2725 | 650 | 0.0011 | - |
|
176 |
+
| 0.2935 | 700 | 0.2077 | - |
|
177 |
+
| 0.3145 | 750 | 0.0025 | - |
|
178 |
+
| 0.3354 | 800 | 0.0014 | - |
|
179 |
+
| 0.3564 | 850 | 0.0011 | - |
|
180 |
+
| 0.3774 | 900 | 0.0028 | - |
|
181 |
+
| 0.3983 | 950 | 0.0004 | - |
|
182 |
+
| 0.4193 | 1000 | 0.0005 | - |
|
183 |
+
| 0.4403 | 1050 | 0.0011 | - |
|
184 |
+
| 0.4612 | 1100 | 0.0011 | - |
|
185 |
+
| 0.4822 | 1150 | 0.0007 | - |
|
186 |
+
| 0.5031 | 1200 | 0.0009 | - |
|
187 |
+
| 0.5241 | 1250 | 0.0161 | - |
|
188 |
+
| 0.5451 | 1300 | 0.0013 | - |
|
189 |
+
| 0.5660 | 1350 | 0.0003 | - |
|
190 |
+
| 0.5870 | 1400 | 0.0003 | - |
|
191 |
+
| 0.6080 | 1450 | 0.0005 | - |
|
192 |
+
| 0.6289 | 1500 | 0.0004 | - |
|
193 |
+
| 0.6499 | 1550 | 0.0003 | - |
|
194 |
+
| 0.6709 | 1600 | 0.0004 | - |
|
195 |
+
| 0.6918 | 1650 | 0.0005 | - |
|
196 |
+
| 0.7128 | 1700 | 0.0005 | - |
|
197 |
+
| 0.7338 | 1750 | 0.0003 | - |
|
198 |
+
| 0.7547 | 1800 | 0.0013 | - |
|
199 |
+
| 0.7757 | 1850 | 0.0004 | - |
|
200 |
+
| 0.7966 | 1900 | 0.0006 | - |
|
201 |
+
| 0.8176 | 1950 | 0.0003 | - |
|
202 |
+
| 0.8386 | 2000 | 0.0003 | - |
|
203 |
+
| 0.8595 | 2050 | 0.0005 | - |
|
204 |
+
| 0.8805 | 2100 | 0.0003 | - |
|
205 |
+
| 0.9015 | 2150 | 0.0005 | - |
|
206 |
+
| 0.9224 | 2200 | 0.0002 | - |
|
207 |
+
| 0.9434 | 2250 | 0.0003 | - |
|
208 |
+
| 0.9644 | 2300 | 0.0003 | - |
|
209 |
+
| 0.9853 | 2350 | 0.0002 | - |
|
210 |
+
|
211 |
+
### Framework Versions
|
212 |
+
- Python: 3.10.13
|
213 |
+
- SetFit: 1.0.3
|
214 |
+
- Sentence Transformers: 3.0.1
|
215 |
+
- spaCy: 3.7.5
|
216 |
+
- Transformers: 4.36.2
|
217 |
+
- PyTorch: 2.1.2
|
218 |
+
- Datasets: 2.19.2
|
219 |
+
- Tokenizers: 0.15.2
|
220 |
+
|
221 |
+
## Citation
|
222 |
+
|
223 |
+
### BibTeX
|
224 |
+
```bibtex
|
225 |
+
@article{https://doi.org/10.48550/arxiv.2209.11055,
|
226 |
+
doi = {10.48550/ARXIV.2209.11055},
|
227 |
+
url = {https://arxiv.org/abs/2209.11055},
|
228 |
+
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
|
229 |
+
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
|
230 |
+
title = {Efficient Few-Shot Learning Without Prompts},
|
231 |
+
publisher = {arXiv},
|
232 |
+
year = {2022},
|
233 |
+
copyright = {Creative Commons Attribution 4.0 International}
|
234 |
+
}
|
235 |
+
```
|
236 |
+
|
237 |
+
<!--
|
238 |
+
## Glossary
|
239 |
+
|
240 |
+
*Clearly define terms in order to be accessible across audiences.*
|
241 |
+
-->
|
242 |
+
|
243 |
+
<!--
|
244 |
+
## Model Card Authors
|
245 |
+
|
246 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
247 |
+
-->
|
248 |
+
|
249 |
+
<!--
|
250 |
+
## Model Card Contact
|
251 |
+
|
252 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
253 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "firqaaa/indo-setfit-absa-bert-base-restaurants-polarity",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 1024,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 4096,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 8194,
|
17 |
+
"model_type": "xlm-roberta",
|
18 |
+
"num_attention_heads": 16,
|
19 |
+
"num_hidden_layers": 24,
|
20 |
+
"output_past": true,
|
21 |
+
"pad_token_id": 1,
|
22 |
+
"position_embedding_type": "absolute",
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.36.2",
|
25 |
+
"type_vocab_size": 1,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 250002
|
28 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "3.0.1",
|
4 |
+
"transformers": "4.36.2",
|
5 |
+
"pytorch": "2.1.2"
|
6 |
+
},
|
7 |
+
"prompts": {},
|
8 |
+
"default_prompt_name": null,
|
9 |
+
"similarity_fn_name": null
|
10 |
+
}
|
config_setfit.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"span_context": 3,
|
3 |
+
"spacy_model": "id_core_news_trf",
|
4 |
+
"normalize_embeddings": false,
|
5 |
+
"labels": [
|
6 |
+
"konflik",
|
7 |
+
"negatif",
|
8 |
+
"netral",
|
9 |
+
"positif"
|
10 |
+
]
|
11 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:777e0b66ef3ef40ab656db0786a1959404e6a702706f0c44fb2b84bec7cfcab1
|
3 |
+
size 2271064456
|
model_head.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44cfee69809f143259668f538363abb3663baebb5a4d3c28741639aa5eec829b
|
3 |
+
size 9087
|
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": 8192,
|
3 |
+
"do_lower_case": false
|
4 |
+
}
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
3 |
+
size 5069051
|
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
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1af481bd08ed9347cf9d3d07c24e5de75a10983819de076436400609e6705686
|
3 |
+
size 17083075
|
tokenizer_config.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"250001": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"bos_token": "<s>",
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "<s>",
|
47 |
+
"eos_token": "</s>",
|
48 |
+
"mask_token": "<mask>",
|
49 |
+
"max_length": 8192,
|
50 |
+
"model_max_length": 8192,
|
51 |
+
"pad_to_multiple_of": null,
|
52 |
+
"pad_token": "<pad>",
|
53 |
+
"pad_token_type_id": 0,
|
54 |
+
"padding_side": "right",
|
55 |
+
"sep_token": "</s>",
|
56 |
+
"sp_model_kwargs": {},
|
57 |
+
"stride": 0,
|
58 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
59 |
+
"truncation_side": "right",
|
60 |
+
"truncation_strategy": "longest_first",
|
61 |
+
"unk_token": "<unk>"
|
62 |
+
}
|