bourdoiscatie
commited on
Commit
•
8cff50b
1
Parent(s):
2bd9067
Training complete
Browse files- .gitattributes +1 -0
- 1_Pooling/config.json +10 -0
- README.md +451 -0
- config.json +28 -0
- config_sentence_transformers.json +10 -0
- model.safetensors +3 -0
- modules.json +14 -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 +54 -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": 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 +1,451 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: intfloat/multilingual-e5-large
|
3 |
+
library_name: sentence-transformers
|
4 |
+
pipeline_tag: sentence-similarity
|
5 |
+
tags:
|
6 |
+
- sentence-transformers
|
7 |
+
- sentence-similarity
|
8 |
+
- feature-extraction
|
9 |
+
- generated_from_trainer
|
10 |
+
- dataset_size:1114945
|
11 |
+
- loss:MultipleNegativesRankingLoss
|
12 |
+
- loss:CoSENTLoss
|
13 |
+
widget:
|
14 |
+
- source_sentence: Quelles sont les exigences pour qu'un objet soit classé comme une
|
15 |
+
planète?
|
16 |
+
sentences:
|
17 |
+
- Ce second scénario pousse certains astronomes, à parler de « planète » à propos
|
18 |
+
de ces objets, puisqu'elles ont été des planètes classiques avant d’être éjectées
|
19 |
+
de leur orbite autour de leur étoile. À l’inverse, d’autres scientifiques nient
|
20 |
+
ce statut car ils défendent l’idée que la définition d’une planète dépend de son
|
21 |
+
état observable immédiat et non de son origine. Ils avancent aussi, pour le premier
|
22 |
+
scénario décrit ici, que ces objets ne seraient donc pas des planètes mais plutôt
|
23 |
+
des naines brunes.
|
24 |
+
- En 2006, lors de la tentative de définition officielle précise du terme « planète
|
25 |
+
» par l'Union astronomique internationale, il fut proposé qu'une planète soit
|
26 |
+
définie comme un corps orbitant autour du Soleil et suffisamment grand pour être
|
27 |
+
de forme globalement sphérique. Selon cette proposition, Charon aurait été considéré
|
28 |
+
comme une planète, puisqu'un satellite aurait été explicitement défini comme tournant
|
29 |
+
autour d'un barycentre situé à l'intérieur du corps principal. La définition finalement
|
30 |
+
adoptée exige qu'une planète ait également éliminé tout objet de taille comparable
|
31 |
+
sur son orbite. Un objet répondant aux précédents critères mais pas au dernier
|
32 |
+
est qualifié de planète naine et Pluton a donc reçu cette nouvelle classification.
|
33 |
+
Charon n'a pas été explicitement classée et reste donc, pour le moment, officiellement
|
34 |
+
considéré comme satellite de Pluton.
|
35 |
+
- La plupart des planeurs sont capables d'effectuer des figures de base de voltige,
|
36 |
+
mais du fait de leur envergure, ils sont moins maniables que les avions. Pour
|
37 |
+
les compétitions, il existe donc des planeurs de voltige, d'envergure moindre
|
38 |
+
donc très maniables, mais dont la finesse plus faible les rend moins apte au vol
|
39 |
+
à voile.
|
40 |
+
- source_sentence: 189 et les coûts d'utilisation sont estimés de la même manière.
|
41 |
+
sentences:
|
42 |
+
- Après avoir regardé autour de ces collections, grimpez la colline jusqu'à la maison
|
43 |
+
de la commissaire, où vous trouverez de belles vues sur la côte environnante et
|
44 |
+
le reste du complexe de l'arsenal maritime.
|
45 |
+
- Ils connaissaient les coûts d'utilisateur exacts.
|
46 |
+
- 189 et les coûts d'utilisation sont estimés de la même manière.
|
47 |
+
- source_sentence: c'est vrai, ils vont passer par la fente
|
48 |
+
sentences:
|
49 |
+
- Ailleurs dans le jardin du prince, dans un bâtiment moderne appelé la Maison du
|
50 |
+
Marin (Casa de Marinos), vous pouvez découvrir ce que devint l'étrange escadre
|
51 |
+
du Tage de la flotte royale.
|
52 |
+
- Ils vont à l'inauguration.
|
53 |
+
- c'est vrai, ils vont passer par la fente
|
54 |
+
- source_sentence: Créer des moments permettant aux parents et aux enfants d'être
|
55 |
+
ensemble constitue un préalable à l'implémentation des idées et des pratiques
|
56 |
+
dont je parle dans ce livre.
|
57 |
+
sentences:
|
58 |
+
- Avant que les Américains n’en prennent le contrôle, Culebra était appelée l'île
|
59 |
+
Vierge espagnole. Elle est située dans les îles Vierges des États-Unis, à mi-chemin
|
60 |
+
entre Puerto Rico et St. Thomas.
|
61 |
+
- Créer des moments permettant aux parents et aux enfants d'être ensemble constitue
|
62 |
+
un préalable à l'implémentation des idées et des pratiques dont je parle dans
|
63 |
+
ce livre.
|
64 |
+
- Ce livre nous explique que les parents ne devraient pas passer de temps avec leurs
|
65 |
+
enfants.
|
66 |
+
- source_sentence: Tenet est sous surveillance depuis novembre, lorsque l'ancien directeur
|
67 |
+
général Jeffrey Barbakow a déclaré que la société a utilisé des prix agressifs
|
68 |
+
pour déclencher des paiements plus élevés pour les patients les plus malades de
|
69 |
+
l'assurance maladie.
|
70 |
+
sentences:
|
71 |
+
- Il est destiné à stimuler la croissance des racines - en particulier à stimuler
|
72 |
+
la création de racines.
|
73 |
+
- En novembre, Jeffrey Brabakow, le directeur général de l'époque, a déclaré que
|
74 |
+
la société utilisait des prix agressifs pour obtenir des paiements plus élevés
|
75 |
+
pour les patients les plus malades de l'assurance maladie.
|
76 |
+
- La femme est en route pour un rendez-vous.
|
77 |
+
---
|
78 |
+
|
79 |
+
# SentenceTransformer based on intfloat/multilingual-e5-large
|
80 |
+
|
81 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [intfloat/multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large). It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
|
82 |
+
|
83 |
+
## Model Details
|
84 |
+
|
85 |
+
### Model Description
|
86 |
+
- **Model Type:** Sentence Transformer
|
87 |
+
- **Base model:** [intfloat/multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large) <!-- at revision ab10c1a7f42e74530fe7ae5be82e6d4f11a719eb -->
|
88 |
+
- **Maximum Sequence Length:** 512 tokens
|
89 |
+
- **Output Dimensionality:** 1024 tokens
|
90 |
+
- **Similarity Function:** Cosine Similarity
|
91 |
+
<!-- - **Training Dataset:** Unknown -->
|
92 |
+
<!-- - **Language:** Unknown -->
|
93 |
+
<!-- - **License:** Unknown -->
|
94 |
+
|
95 |
+
### Model Sources
|
96 |
+
|
97 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
98 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
99 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
100 |
+
|
101 |
+
### Full Model Architecture
|
102 |
+
|
103 |
+
```
|
104 |
+
SentenceTransformer(
|
105 |
+
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: XLMRobertaModel
|
106 |
+
(1): Pooling({'word_embedding_dimension': 1024, '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})
|
107 |
+
)
|
108 |
+
```
|
109 |
+
|
110 |
+
## Usage
|
111 |
+
|
112 |
+
### Direct Usage (Sentence Transformers)
|
113 |
+
|
114 |
+
First install the Sentence Transformers library:
|
115 |
+
|
116 |
+
```bash
|
117 |
+
pip install -U sentence-transformers
|
118 |
+
```
|
119 |
+
|
120 |
+
Then you can load this model and run inference.
|
121 |
+
```python
|
122 |
+
from sentence_transformers import SentenceTransformer
|
123 |
+
|
124 |
+
# Download from the 🤗 Hub
|
125 |
+
model = SentenceTransformer("bourdoiscatie/multilingual-e5-large-approche5")
|
126 |
+
# Run inference
|
127 |
+
sentences = [
|
128 |
+
"Tenet est sous surveillance depuis novembre, lorsque l'ancien directeur général Jeffrey Barbakow a déclaré que la société a utilisé des prix agressifs pour déclencher des paiements plus élevés pour les patients les plus malades de l'assurance maladie.",
|
129 |
+
"En novembre, Jeffrey Brabakow, le directeur général de l'époque, a déclaré que la société utilisait des prix agressifs pour obtenir des paiements plus élevés pour les patients les plus malades de l'assurance maladie.",
|
130 |
+
'La femme est en route pour un rendez-vous.',
|
131 |
+
]
|
132 |
+
embeddings = model.encode(sentences)
|
133 |
+
print(embeddings.shape)
|
134 |
+
# [3, 1024]
|
135 |
+
|
136 |
+
# Get the similarity scores for the embeddings
|
137 |
+
similarities = model.similarity(embeddings, embeddings)
|
138 |
+
print(similarities.shape)
|
139 |
+
# [3, 3]
|
140 |
+
```
|
141 |
+
|
142 |
+
<!--
|
143 |
+
### Direct Usage (Transformers)
|
144 |
+
|
145 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
146 |
+
|
147 |
+
</details>
|
148 |
+
-->
|
149 |
+
|
150 |
+
<!--
|
151 |
+
### Downstream Usage (Sentence Transformers)
|
152 |
+
|
153 |
+
You can finetune this model on your own dataset.
|
154 |
+
|
155 |
+
<details><summary>Click to expand</summary>
|
156 |
+
|
157 |
+
</details>
|
158 |
+
-->
|
159 |
+
|
160 |
+
<!--
|
161 |
+
### Out-of-Scope Use
|
162 |
+
|
163 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
164 |
+
-->
|
165 |
+
|
166 |
+
<!--
|
167 |
+
## Bias, Risks and Limitations
|
168 |
+
|
169 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
170 |
+
-->
|
171 |
+
|
172 |
+
<!--
|
173 |
+
### Recommendations
|
174 |
+
|
175 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
176 |
+
-->
|
177 |
+
|
178 |
+
## Training Details
|
179 |
+
|
180 |
+
### Training Hyperparameters
|
181 |
+
#### Non-Default Hyperparameters
|
182 |
+
|
183 |
+
- `eval_strategy`: epoch
|
184 |
+
- `learning_rate`: 1e-05
|
185 |
+
- `weight_decay`: 0.01
|
186 |
+
- `num_train_epochs`: 1
|
187 |
+
- `batch_sampler`: no_duplicates
|
188 |
+
|
189 |
+
#### All Hyperparameters
|
190 |
+
<details><summary>Click to expand</summary>
|
191 |
+
|
192 |
+
- `overwrite_output_dir`: False
|
193 |
+
- `do_predict`: False
|
194 |
+
- `eval_strategy`: epoch
|
195 |
+
- `prediction_loss_only`: True
|
196 |
+
- `per_device_train_batch_size`: 8
|
197 |
+
- `per_device_eval_batch_size`: 8
|
198 |
+
- `per_gpu_train_batch_size`: None
|
199 |
+
- `per_gpu_eval_batch_size`: None
|
200 |
+
- `gradient_accumulation_steps`: 1
|
201 |
+
- `eval_accumulation_steps`: None
|
202 |
+
- `torch_empty_cache_steps`: None
|
203 |
+
- `learning_rate`: 1e-05
|
204 |
+
- `weight_decay`: 0.01
|
205 |
+
- `adam_beta1`: 0.9
|
206 |
+
- `adam_beta2`: 0.999
|
207 |
+
- `adam_epsilon`: 1e-08
|
208 |
+
- `max_grad_norm`: 1.0
|
209 |
+
- `num_train_epochs`: 1
|
210 |
+
- `max_steps`: -1
|
211 |
+
- `lr_scheduler_type`: linear
|
212 |
+
- `lr_scheduler_kwargs`: {}
|
213 |
+
- `warmup_ratio`: 0.0
|
214 |
+
- `warmup_steps`: 0
|
215 |
+
- `log_level`: passive
|
216 |
+
- `log_level_replica`: warning
|
217 |
+
- `log_on_each_node`: True
|
218 |
+
- `logging_nan_inf_filter`: True
|
219 |
+
- `save_safetensors`: True
|
220 |
+
- `save_on_each_node`: False
|
221 |
+
- `save_only_model`: False
|
222 |
+
- `restore_callback_states_from_checkpoint`: False
|
223 |
+
- `no_cuda`: False
|
224 |
+
- `use_cpu`: False
|
225 |
+
- `use_mps_device`: False
|
226 |
+
- `seed`: 42
|
227 |
+
- `data_seed`: None
|
228 |
+
- `jit_mode_eval`: False
|
229 |
+
- `use_ipex`: False
|
230 |
+
- `bf16`: False
|
231 |
+
- `fp16`: False
|
232 |
+
- `fp16_opt_level`: O1
|
233 |
+
- `half_precision_backend`: auto
|
234 |
+
- `bf16_full_eval`: False
|
235 |
+
- `fp16_full_eval`: False
|
236 |
+
- `tf32`: None
|
237 |
+
- `local_rank`: 0
|
238 |
+
- `ddp_backend`: None
|
239 |
+
- `tpu_num_cores`: None
|
240 |
+
- `tpu_metrics_debug`: False
|
241 |
+
- `debug`: []
|
242 |
+
- `dataloader_drop_last`: False
|
243 |
+
- `dataloader_num_workers`: 0
|
244 |
+
- `dataloader_prefetch_factor`: None
|
245 |
+
- `past_index`: -1
|
246 |
+
- `disable_tqdm`: False
|
247 |
+
- `remove_unused_columns`: True
|
248 |
+
- `label_names`: None
|
249 |
+
- `load_best_model_at_end`: False
|
250 |
+
- `ignore_data_skip`: False
|
251 |
+
- `fsdp`: []
|
252 |
+
- `fsdp_min_num_params`: 0
|
253 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
254 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
255 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
256 |
+
- `deepspeed`: None
|
257 |
+
- `label_smoothing_factor`: 0.0
|
258 |
+
- `optim`: adamw_torch
|
259 |
+
- `optim_args`: None
|
260 |
+
- `adafactor`: False
|
261 |
+
- `group_by_length`: False
|
262 |
+
- `length_column_name`: length
|
263 |
+
- `ddp_find_unused_parameters`: None
|
264 |
+
- `ddp_bucket_cap_mb`: None
|
265 |
+
- `ddp_broadcast_buffers`: False
|
266 |
+
- `dataloader_pin_memory`: True
|
267 |
+
- `dataloader_persistent_workers`: False
|
268 |
+
- `skip_memory_metrics`: True
|
269 |
+
- `use_legacy_prediction_loop`: False
|
270 |
+
- `push_to_hub`: False
|
271 |
+
- `resume_from_checkpoint`: None
|
272 |
+
- `hub_model_id`: None
|
273 |
+
- `hub_strategy`: every_save
|
274 |
+
- `hub_private_repo`: False
|
275 |
+
- `hub_always_push`: False
|
276 |
+
- `gradient_checkpointing`: False
|
277 |
+
- `gradient_checkpointing_kwargs`: None
|
278 |
+
- `include_inputs_for_metrics`: False
|
279 |
+
- `eval_do_concat_batches`: True
|
280 |
+
- `fp16_backend`: auto
|
281 |
+
- `push_to_hub_model_id`: None
|
282 |
+
- `push_to_hub_organization`: None
|
283 |
+
- `mp_parameters`:
|
284 |
+
- `auto_find_batch_size`: False
|
285 |
+
- `full_determinism`: False
|
286 |
+
- `torchdynamo`: None
|
287 |
+
- `ray_scope`: last
|
288 |
+
- `ddp_timeout`: 1800
|
289 |
+
- `torch_compile`: False
|
290 |
+
- `torch_compile_backend`: None
|
291 |
+
- `torch_compile_mode`: None
|
292 |
+
- `dispatch_batches`: None
|
293 |
+
- `split_batches`: None
|
294 |
+
- `include_tokens_per_second`: False
|
295 |
+
- `include_num_input_tokens_seen`: False
|
296 |
+
- `neftune_noise_alpha`: None
|
297 |
+
- `optim_target_modules`: None
|
298 |
+
- `batch_eval_metrics`: False
|
299 |
+
- `eval_on_start`: False
|
300 |
+
- `use_liger_kernel`: False
|
301 |
+
- `eval_use_gather_object`: False
|
302 |
+
- `batch_sampler`: no_duplicates
|
303 |
+
- `multi_dataset_batch_sampler`: proportional
|
304 |
+
|
305 |
+
</details>
|
306 |
+
|
307 |
+
### Training Logs
|
308 |
+
| Epoch | Step | Training Loss | nli loss | sts loss | triplet loss |
|
309 |
+
|:------:|:-----:|:-------------:|:--------:|:--------:|:------------:|
|
310 |
+
| 0.0137 | 500 | 2.3683 | - | - | - |
|
311 |
+
| 0.0273 | 1000 | 2.2564 | - | - | - |
|
312 |
+
| 0.0410 | 1500 | 2.3976 | - | - | - |
|
313 |
+
| 0.0547 | 2000 | 2.1925 | - | - | - |
|
314 |
+
| 0.0684 | 2500 | 2.1542 | - | - | - |
|
315 |
+
| 0.0820 | 3000 | 2.0945 | - | - | - |
|
316 |
+
| 0.0957 | 3500 | 2.1411 | - | - | - |
|
317 |
+
| 0.1094 | 4000 | 1.9079 | - | - | - |
|
318 |
+
| 0.1231 | 4500 | 1.7574 | - | - | - |
|
319 |
+
| 0.1367 | 5000 | 2.1923 | - | - | - |
|
320 |
+
| 0.1504 | 5500 | 2.0054 | - | - | - |
|
321 |
+
| 0.1641 | 6000 | 1.6717 | - | - | - |
|
322 |
+
| 0.1778 | 6500 | 1.7374 | - | - | - |
|
323 |
+
| 0.1914 | 7000 | 2.0042 | - | - | - |
|
324 |
+
| 0.2051 | 7500 | 1.7486 | - | - | - |
|
325 |
+
| 0.2188 | 8000 | 1.5635 | - | - | - |
|
326 |
+
| 0.2324 | 8500 | 1.8133 | - | - | - |
|
327 |
+
| 0.2461 | 9000 | 1.7885 | - | - | - |
|
328 |
+
| 0.2598 | 9500 | 1.6298 | - | - | - |
|
329 |
+
| 0.2735 | 10000 | 1.3568 | - | - | - |
|
330 |
+
| 0.2871 | 10500 | 1.8475 | - | - | - |
|
331 |
+
| 0.3008 | 11000 | 1.7642 | - | - | - |
|
332 |
+
| 0.3145 | 11500 | 1.4048 | - | - | - |
|
333 |
+
| 0.3282 | 12000 | 1.3782 | - | - | - |
|
334 |
+
| 0.3418 | 12500 | 1.8164 | - | - | - |
|
335 |
+
| 0.3555 | 13000 | 1.5559 | - | - | - |
|
336 |
+
| 0.3692 | 13500 | 1.2515 | - | - | - |
|
337 |
+
| 0.3828 | 14000 | 1.4736 | - | - | - |
|
338 |
+
| 0.3965 | 14500 | 1.5527 | - | - | - |
|
339 |
+
| 0.4102 | 15000 | 1.384 | - | - | - |
|
340 |
+
| 0.4239 | 15500 | 1.167 | - | - | - |
|
341 |
+
| 0.4375 | 16000 | 1.6116 | - | - | - |
|
342 |
+
| 0.4512 | 16500 | 1.5668 | - | - | - |
|
343 |
+
| 0.4649 | 17000 | 1.1458 | - | - | - |
|
344 |
+
| 0.4786 | 17500 | 1.1103 | - | - | - |
|
345 |
+
| 0.4922 | 18000 | 1.6152 | - | - | - |
|
346 |
+
| 0.5059 | 18500 | 1.347 | - | - | - |
|
347 |
+
| 0.5196 | 19000 | 1.1 | - | - | - |
|
348 |
+
| 0.5333 | 19500 | 1.2662 | - | - | - |
|
349 |
+
| 0.5469 | 20000 | 1.456 | - | - | - |
|
350 |
+
| 0.5606 | 20500 | 1.1928 | - | - | - |
|
351 |
+
| 0.5743 | 21000 | 0.9972 | - | - | - |
|
352 |
+
| 0.5879 | 21500 | 1.4499 | - | - | - |
|
353 |
+
| 0.6016 | 22000 | 1.3264 | - | - | - |
|
354 |
+
| 0.6153 | 22500 | 1.003 | - | - | - |
|
355 |
+
| 0.6290 | 23000 | 1.0512 | - | - | - |
|
356 |
+
| 0.6426 | 23500 | 1.3041 | - | - | - |
|
357 |
+
| 0.6563 | 24000 | 1.1227 | - | - | - |
|
358 |
+
| 0.6700 | 24500 | 0.9579 | - | - | - |
|
359 |
+
| 0.6837 | 25000 | 1.1196 | - | - | - |
|
360 |
+
| 0.6973 | 25500 | 1.1362 | - | - | - |
|
361 |
+
| 0.7110 | 26000 | 1.0376 | - | - | - |
|
362 |
+
| 0.7247 | 26500 | 0.8037 | - | - | - |
|
363 |
+
| 0.7384 | 27000 | 1.2622 | - | - | - |
|
364 |
+
| 0.7520 | 27500 | 1.1696 | - | - | - |
|
365 |
+
| 0.7657 | 28000 | 0.8923 | - | - | - |
|
366 |
+
| 0.7794 | 28500 | 0.8389 | - | - | - |
|
367 |
+
| 0.7930 | 29000 | 1.2655 | - | - | - |
|
368 |
+
| 0.8067 | 29500 | 0.965 | - | - | - |
|
369 |
+
| 0.8204 | 30000 | 0.8043 | - | - | - |
|
370 |
+
| 0.8341 | 30500 | 1.0491 | - | - | - |
|
371 |
+
| 0.8477 | 31000 | 1.1186 | - | - | - |
|
372 |
+
| 0.8614 | 31500 | 0.8794 | - | - | - |
|
373 |
+
| 0.8751 | 32000 | 0.7776 | - | - | - |
|
374 |
+
| 0.8888 | 32500 | 1.1299 | - | - | - |
|
375 |
+
| 0.9024 | 33000 | 0.9544 | - | - | - |
|
376 |
+
| 0.9161 | 33500 | 0.7195 | - | - | - |
|
377 |
+
| 0.9298 | 34000 | 0.8298 | - | - | - |
|
378 |
+
| 0.9434 | 34500 | 1.0767 | - | - | - |
|
379 |
+
| 0.9571 | 35000 | 0.8287 | - | - | - |
|
380 |
+
| 0.9708 | 35500 | 0.7331 | - | - | - |
|
381 |
+
| 0.9845 | 36000 | 0.904 | - | - | - |
|
382 |
+
| 0.9981 | 36500 | 0.9645 | - | - | - |
|
383 |
+
| 1.0 | 36568 | - | 0.0193 | 5.4479 | 0.5933 |
|
384 |
+
|
385 |
+
|
386 |
+
### Framework Versions
|
387 |
+
- Python: 3.12.6
|
388 |
+
- Sentence Transformers: 3.1.1
|
389 |
+
- Transformers: 4.45.2
|
390 |
+
- PyTorch: 2.4.0+cu121
|
391 |
+
- Accelerate: 0.29.3
|
392 |
+
- Datasets: 3.0.2
|
393 |
+
- Tokenizers: 0.20.1
|
394 |
+
|
395 |
+
## Citation
|
396 |
+
|
397 |
+
### BibTeX
|
398 |
+
|
399 |
+
#### Sentence Transformers
|
400 |
+
```bibtex
|
401 |
+
@inproceedings{reimers-2019-sentence-bert,
|
402 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
403 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
404 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
405 |
+
month = "11",
|
406 |
+
year = "2019",
|
407 |
+
publisher = "Association for Computational Linguistics",
|
408 |
+
url = "https://arxiv.org/abs/1908.10084",
|
409 |
+
}
|
410 |
+
```
|
411 |
+
|
412 |
+
#### MultipleNegativesRankingLoss
|
413 |
+
```bibtex
|
414 |
+
@misc{henderson2017efficient,
|
415 |
+
title={Efficient Natural Language Response Suggestion for Smart Reply},
|
416 |
+
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},
|
417 |
+
year={2017},
|
418 |
+
eprint={1705.00652},
|
419 |
+
archivePrefix={arXiv},
|
420 |
+
primaryClass={cs.CL}
|
421 |
+
}
|
422 |
+
```
|
423 |
+
|
424 |
+
#### CoSENTLoss
|
425 |
+
```bibtex
|
426 |
+
@online{kexuefm-8847,
|
427 |
+
title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
|
428 |
+
author={Su Jianlin},
|
429 |
+
year={2022},
|
430 |
+
month={Jan},
|
431 |
+
url={https://kexue.fm/archives/8847},
|
432 |
+
}
|
433 |
+
```
|
434 |
+
|
435 |
+
<!--
|
436 |
+
## Glossary
|
437 |
+
|
438 |
+
*Clearly define terms in order to be accessible across audiences.*
|
439 |
+
-->
|
440 |
+
|
441 |
+
<!--
|
442 |
+
## Model Card Authors
|
443 |
+
|
444 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
445 |
+
-->
|
446 |
+
|
447 |
+
<!--
|
448 |
+
## Model Card Contact
|
449 |
+
|
450 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
451 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "intfloat/multilingual-e5-large",
|
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": 514,
|
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": "4.45.2",
|
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": "3.1.1",
|
4 |
+
"transformers": "4.45.2",
|
5 |
+
"pytorch": "2.4.0+cu121"
|
6 |
+
},
|
7 |
+
"prompts": {},
|
8 |
+
"default_prompt_name": null,
|
9 |
+
"similarity_fn_name": null
|
10 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7038d674f0b1f2de13a55b40ea354f65ddb68dea5dc589bf77c76fff2ded65ae
|
3 |
+
size 2239607176
|
modules.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[
|
2 |
+
{
|
3 |
+
"idx": 0,
|
4 |
+
"name": "0",
|
5 |
+
"path": "",
|
6 |
+
"type": "__main__.CustomTransformer"
|
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 |
+
}
|
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 sha256:883b037111086fd4dfebbbc9b7cee11e1517b5e0c0514879478661440f137085
|
3 |
+
size 17082987
|
tokenizer_config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"model_max_length": 512,
|
50 |
+
"pad_token": "<pad>",
|
51 |
+
"sep_token": "</s>",
|
52 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
53 |
+
"unk_token": "<unk>"
|
54 |
+
}
|