Hugging Face's logo

carlesoctav
/
SentimentClassifierDune

Text Classification
setfit
Safetensors
sentence-transformers
English
mpnet
generated_from_setfit_trainer
Model card Files Community
carlesoctav commited on
Commit
023d036
•
1 Parent(s): 74e03c8

Add SetFit model

Browse files
Files changed (13) hide show
  1. 1_Pooling/config.json +10 -0
  2. README.md +249 -0
  3. config.json +24 -0
  4. config_sentence_transformers.json +9 -0
  5. config_setfit.json +7 -0
  6. model.safetensors +3 -0
  7. model_head.pkl +3 -0
  8. modules.json +14 -0
  9. sentence_bert_config.json +4 -0
  10. special_tokens_map.json +51 -0
  11. tokenizer.json +0 -0
  12. tokenizer_config.json +66 -0
  13. 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 +1,249 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ license: apache-2.0
4
+ library_name: setfit
5
+ tags:
6
+ - setfit
7
+ - sentence-transformers
8
+ - text-classification
9
+ - generated_from_setfit_trainer
10
+ base_model: sentence-transformers/paraphrase-mpnet-base-v2
11
+ metrics:
12
+ - accuracy
13
+ widget:
14
+ - text: great movie, so close to perfection let me get this straight. this is a brilliant
15
+ brilliant refreshingly brutal movie.i'm glad they didn't soften the general malevolence,
16
+ but i feel they missed out on what i consider the most pivotal point of the book.paul
17
+ drinks the water of life. with it his genetic memory is unlocked, he can foresee
18
+ the actions of people in the future. the golden path is laid out. and so pursues
19
+ the mind altering awakening, leaving him a husk; trapped in one path of fate -
20
+ trapped between his own ego and the true path needed for humanity. in the movie,
21
+ paul drink bad, paul wake up. paul president with superpower!i understand that
22
+ it's a very hard thing to portray for an audience but i think i was just really
23
+ hoping for villeneuve to emphasise the importance of that part and it felt quite
24
+ rushed in that regard.but i doubt they'll make a movie about a big virgin worm
25
+ so prescience might not matter too much.
26
+ - text: absolutely breathtaking the movie is the complete cinematic experience. i
27
+ loved every single line every moment every little thing that makes this movie.the
28
+ only thing that is bothering me is the thirst so bad for the next part.i felt
29
+ like i was in the movie riding a sand worm, i was a fremen. i felt the pain the
30
+ wonder the joy the anger. this felt like reading the book and you just can't stop.
31
+ the excellence of this movie is not only the cast or the story it is the very
32
+ making of it. i loved every dialogue that was uttered. its just a masterpiece.though
33
+ there is a stagnant pace in between it doesn't seem to matter. because most of
34
+ the second part of the movie is such a cliff hanger. 6 out of 10 found this helpful.
35
+ was this review helpful? sign in to vote. permalink
36
+ - text: 'let''s be serious, guys.. appreciate that everyone is entitled to their opinion,
37
+ so here''s mine: anyone giving this less than a solid 9 needs to re-evaluate themselves
38
+ as a person. because you either have no imagination or are just generally a negative
39
+ human. this film has everything and is a modern day great. easily the best cinematic
40
+ experience i''ve ever had, comparable to films like the dark knight trilogy and
41
+ the original star wars films.for a nearly three hour long film, basically nobody
42
+ got up to go for a toilet break and the entire time i felt totally present, gripped
43
+ by it.don''t listen to anyone on here leaving poor reviews. go and watch the film
44
+ and see the magic for yourself. 8 out of 13 found this helpful. was this review
45
+ helpful? sign in to vote. permalink'
46
+ - text: phenomenal this movie was particularly gorgeous and exciting giving all the
47
+ key moments and suspense that anybody of the sort would love, this movie brings
48
+ the suspense and excitement to keep you engaged and always cautious of what's
49
+ next, a truly wonderful story that is acted so perfectly and well, this adaptation
50
+ has brung the story alive and in the spotlight proving there is not only a lot
51
+ to it but also that it has a lot more to come and personally i want to see it
52
+ all. i left the theater thoroughly wanting even more for the story and continuing
53
+ on that i can't wait for what is to come of this movie. it is truly a must watch
54
+ masterpiece. 4 out of 6 found this helpful. was this review helpful? sign in to
55
+ vote. permalink
56
+ - text: film of the decade i've always wished to watch films like lord of the rings
57
+ and star wars in theaters, but i was simply born too late. dune 2 made me feel
58
+ like i was watching those movies in theaters, the epic sweaping shots, the massive
59
+ amount of extras, the attention to detail, the costumes, every single fight looked
60
+ like they spent days choreographing it. the soundtrack was the best i heard since
61
+ interstellar, and it matched the mood at every point. honestly i thought film
62
+ was going down, disney is losing it and they own almost everything. but dune 2
63
+ restored my hope in movies and actually made me want to pursue a career in film.
64
+ overall, this movie was epic and easily deserves a 10 star rating. 1 out of 1
65
+ found this helpful. was this review helpful? sign in to vote. permalink
66
+ pipeline_tag: text-classification
67
+ inference: true
68
+ ---
69
+
70
+ # SetFit with sentence-transformers/paraphrase-mpnet-base-v2 on data/raw/15239678.jsonl
71
+
72
+ This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2) as the Sentence Transformer embedding model. A [SetFitHead](huggingface.co/docs/setfit/reference/main#setfit.SetFitHead) instance is used for classification.
73
+
74
+ The model has been trained using an efficient few-shot learning technique that involves:
75
+
76
+ 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
77
+ 2. Training a classification head with features from the fine-tuned Sentence Transformer.
78
+
79
+ ## Model Details
80
+
81
+ ### Model Description
82
+ - **Model Type:** SetFit
83
+ - **Sentence Transformer body:** [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2)
84
+ - **Classification head:** a [SetFitHead](huggingface.co/docs/setfit/reference/main#setfit.SetFitHead) instance
85
+ - **Maximum Sequence Length:** 512 tokens
86
+ - **Number of Classes:** 2 classes
87
+ <!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
88
+ - **Language:** en
89
+ - **License:** apache-2.0
90
+
91
+ ### Model Sources
92
+
93
+ - **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
94
+ - **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
95
+ - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
96
+
97
+ ### Model Labels
98
+ | Label | Examples |
99
+ |:---------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
100
+ | positive | <ul><li>"good sequel dune part ii is a very good sequel. the world building in this movie is great and really establishes the fremen culture. i love how the movie dives deep into how they view culture and religion and the split that they have over their belief in paul. timothee chalamet is excellent as paul atreides. his character arc is amazing. he starts off as someone who just wants to help and then through his time with the fremen he starts to use them and their faith to get his own revenge. zendaya was also great and her character's dynamic with paul was very fleshed out. i loved how she went from loving him to despising what he represents. florence pugh was a good addition here although she didn't have much to do. austin butler stole the show in my opinion. he was a perfect villain and his pure psychotic nature was frightening. the costumes, visual effects, and set design all looked great. i especially love the design of the black and white planet. there were a lot of cool things they did with it, like the fireworks for example. the action scenes are pretty good. the cinematography is very good and denis villeneuve crushed it directing. hans zimmer delivers a killer score here as he always does. i only have a few minor issues with the movie. just like the first movie i think the pacing was a little off and despite rebecca ferguson giving a great performance i didn't really think her storyline was that interesting or well explained. overall dune part ii is a really good movie and if you liked the first one you'll have a great time here."</li><li>"am i the only one who's not seeing it? i mean, yeah, it's very entertaining and, of course, very visually stunning. the set pieces, the cinematography, the use of visual effects and lights, the sound design and music, all, absolutely amazing and almost literally stunning!but then? i'm not really seeing much after that. as i have not read the books, this movie was a total mystery to me. there's barely any dialog--at least not any that would explain anything what's going on at all. the world and the technology etc just doesn't make much sense to me.none of the characters are particularly interesting, to be honest. they don't really have that much personality to them, and even if they did, they didn't really make me care about them all that much.i don't know, i'm a bit conflicted, it wasn't a bad movie and, as i said, it was entertaining and visually mesmerizing, but it lacked the depth that i was expecting of a world this size and this rich with lore and history. maybe the movie makers assumed everyone has read the books? as someone to who the world is not familiar at all, it just seems rather confusing and strange. i feel like they just focused on making it as visually awesome as they can (in which they arguably succeeded), but left the story on the pages of the books."</li><li>'dune: part two it\'s totally amazing best sf movie i just saw the new movie "dune: part two" and i was speechless.it was amazing, full of creativity and an unforgettable action.from the sensational footage, which i will constantly praise, to the story and everything that the dune universe means.shocking scenes, dramatic scenes, romantic scenes but also full scenes, full of action, carnage and explosions.something i\'ve been waiting for so long and it was more perfect than i expected...in imax, the sound was so good that at any explosion or need for bass, it creates a shock, an earthquake that gives incredible pleasure.you must see it and i declare that it is the best film of 2024 and i don\'t think that any of the upcoming movies will be better. waiting for oscars and all the wins possible .'</li></ul> |
101
+ | negative | <ul><li>'boring, wow, so very boring ...i walked out about 2hrs in because i just couldn\'t anymore.i don\'t understand how a movie with so much time and space could possibly exclude so much and move the plot so little.no storytelling: it feels like an extended montage where paul\'s cheerleading base grows along with his relationship with chani but we don\'t know how or why.poorly written: female leads felt like wallpaper rather than the badass characters who carry paul through the book. some reviews here are saying the movie was true to the book, which i don\'t understand because they also don\'t even touch on the space guild.vapid acting: paul. bautista can only scream? everyone seemed demoralized in their roles (i would be too if i was zendaya, rebecca ferguson, or anyone else who actually wanted to embrace the role of a lifetime and was so absolutely diminished)."cinematography": i must be hard to get more than a handful of creative shots of sand. what was happening on the harkonnen home world? honestly the blown out black and white scene felt really lazy and cheap. at least after that there was more desert.christopher walken: was his casting supposed to be some sort of meta joke? even his performance rang flat. i thought the emperor was supposed to be eternally young due to spice consumption. how this character is supposed to be the center / leader of the universe is anyone\'s guess.i\'ll wait until it\'s streaming and finish at my convenience to see if any of this gets salvaged, i just can\'t imagine how it could be.'</li><li>"great i you didn't read the books short spoiler-free version: a was really looking forward to this movie. having read the books multiple times, i left the cinema feeling cheated en confused. granted the visuals and the music are astounding. the actors perform very well and the story is fine if haven't read the books. and there's the problem. i you, like me, have read the book you will be thinking 'why?' every 10 minutes or so. villeneuve has made so many changes to the story, i hardly recognize it as dune anymore. and that makes me sad. i try to view the movie and the book as separate things. but how many changes can one make in the story before it deviates to much? after all it is a movie adaptation of the book, there should be enough of it you can recognize. in this the director has, sadly, mist the marc.after the movie i kept sitting staring as the credits rolled by, i was the last one to leave an i felt cheated and sad. my advice is, if you love the books, wait for the streaming services to pick it up. if you haven't read the books, go an see it, you'll love it although perhaps it might be a bit long for your taste.longer version (spoilers!) so, what went wrong? is do understand that you have tot make some choices in what you keep en leave out in the story when making a story. you merge some characters, leave some out. delete scenes that a nice but not really necessary in the main plotline. (like the banket-scene in the first movie). but villenueve and the writers have made al lot of changes that impact the story in so much that is totally deviates from the book. as a fan i can not get my head around soms of them: chani is not supporting at all of paul, she is mostly angry and against all that paul wants tot do. the actors try there best but i miss the chemistry from the previous adaptations and the books. in the ending there is no 'we are concubines' scene. chani leaves paul and rides out in the dessert. why?jessica in the books is a strong well trained bene gesserit. in the movie she goes from a weak, sniveling, manipulative woman. not the strong reverent mother who takes care of het people en supports paul and grows closer tot chani. i can't understand why.stilgar in the books is a strong and wise leader who teaches paul and gradually gives him his trust. in the movie he is transformed into an religious zealot from the south of arrakis, were all fremen blindly believe in the prophecy. (in the north the fremen are non-believers, essentially making it 2 different tribes of fremen, again why?).and then there is no mention of the ecological theme, instead of the water of life they threaten with nukes on the spicefields, no spicing guild and a feeble weak emperor (poor christhoper walken, he tries)) i can get why feyd is changed into a psychopath (not much change from the books) and why hawat and alia are left out completely (sad but understandable). but the rest? as i stated, i feld robbed, sad and very disappointed. it could have been better, but is was a mocking of the real thing."</li><li>"the whole movie happens in slow motion once you realize that the movie is happening in slow motion, you can't un-see it:slowly pan over beautiful landscape, close-up of someone's face. talk. very. slowly. one. word ..... at a time. pan out. bwaaaap/loud noise, next scene, rinse and repeat, stir in the occasional action scene.there are a lot of dialog scenes in this movie, but not much is said. i understand that the book is both thick and dense, so showing everything in slow motion seems an odd choice. i honestly think, if you watch this at home, you could watch it at 2x speed and it might be a decent way to spend an hour and 15 minutes.the battle scenes were also kinda dumb. this is ~8000 years in the future, inter-galactic space flight exists, planes, helicopters, nuclear warheads, guns, lazers, bazookas and more all exist, yet people decide to go to battle as if it's the middle ages - fighting with knives! you don't need to be a messiah to realize that you could bring guns to a knife fight. i'll give them poetic liscense on this one and perhaps we can write it off to the aesthetics, but it did make some of the scenes a little laughable once you realize what's going on. maybe they explain this in the book?i did not enjoy dune 1 for much the same reasons, but so many people were saying this one was better. fool me once, shame on you. fool me twice, shame on me! i will not be fooled a third time!"</li></ul> |
102
+
103
+ ## Uses
104
+
105
+ ### Direct Use for Inference
106
+
107
+ First install the SetFit library:
108
+
109
+ ```bash
110
+ pip install setfit
111
+ ```
112
+
113
+ Then you can load this model and run inference.
114
+
115
+ ```python
116
+ from setfit import SetFitModel
117
+
118
+ # Download from the 🤗 Hub
119
+ model = SetFitModel.from_pretrained("carlesoctav/SentimentClassifierDune")
120
+ # Run inference
121
+ preds = model("phenomenal this movie was particularly gorgeous and exciting giving all the key moments and suspense that anybody of the sort would love, this movie brings the suspense and excitement to keep you engaged and always cautious of what's next, a truly wonderful story that is acted so perfectly and well, this adaptation has brung the story alive and in the spotlight proving there is not only a lot to it but also that it has a lot more to come and personally i want to see it all. i left the theater thoroughly wanting even more for the story and continuing on that i can't wait for what is to come of this movie. it is truly a must watch masterpiece. 4 out of 6 found this helpful. was this review helpful? sign in to vote. permalink")
122
+ ```
123
+
124
+ <!--
125
+ ### Downstream Use
126
+
127
+ *List how someone could finetune this model on their own dataset.*
128
+ -->
129
+
130
+ <!--
131
+ ### Out-of-Scope Use
132
+
133
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
134
+ -->
135
+
136
+ <!--
137
+ ## Bias, Risks and Limitations
138
+
139
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
140
+ -->
141
+
142
+ <!--
143
+ ### Recommendations
144
+
145
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
146
+ -->
147
+
148
+ ## Training Details
149
+
150
+ ### Training Set Metrics
151
+ | Training set | Min | Median | Max |
152
+ |:-------------|:----|:---------|:----|
153
+ | Word count | 107 | 215.2273 | 972 |
154
+
155
+ | Label | Training Sample Count |
156
+ |:---------|:----------------------|
157
+ | negative | 99 |
158
+ | positive | 99 |
159
+
160
+ ### Training Hyperparameters
161
+ - batch_size: (16, 16)
162
+ - num_epochs: (1, 1)
163
+ - max_steps: -1
164
+ - sampling_strategy: oversampling
165
+ - body_learning_rate: (2e-05, 1e-05)
166
+ - head_learning_rate: 0.01
167
+ - loss: CosineSimilarityLoss
168
+ - distance_metric: cosine_distance
169
+ - margin: 0.25
170
+ - end_to_end: False
171
+ - use_amp: False
172
+ - warmup_proportion: 0.1
173
+ - seed: 42
174
+ - eval_max_steps: -1
175
+ - load_best_model_at_end: True
176
+
177
+ ### Training Results
178
+ | Epoch | Step | Training Loss | Validation Loss |
179
+ |:-------:|:--------:|:-------------:|:---------------:|
180
+ | 0.0008 | 1 | 0.2606 | - |
181
+ | 0.0404 | 50 | 0.1578 | - |
182
+ | 0.0808 | 100 | 0.0066 | - |
183
+ | 0.1212 | 150 | 0.0004 | - |
184
+ | 0.1616 | 200 | 0.0003 | - |
185
+ | 0.2019 | 250 | 0.0005 | - |
186
+ | 0.2423 | 300 | 0.0002 | - |
187
+ | 0.2827 | 350 | 0.0003 | - |
188
+ | 0.3231 | 400 | 0.0001 | - |
189
+ | 0.3635 | 450 | 0.0001 | - |
190
+ | 0.4039 | 500 | 0.0001 | - |
191
+ | 0.4443 | 550 | 0.0001 | - |
192
+ | 0.4847 | 600 | 0.0 | - |
193
+ | 0.5250 | 650 | 0.0 | - |
194
+ | 0.5654 | 700 | 0.0 | - |
195
+ | 0.6058 | 750 | 0.0 | - |
196
+ | 0.6462 | 800 | 0.0 | - |
197
+ | 0.6866 | 850 | 0.0 | - |
198
+ | 0.7270 | 900 | 0.0 | - |
199
+ | 0.7674 | 950 | 0.0 | - |
200
+ | 0.8078 | 1000 | 0.0 | - |
201
+ | 0.8481 | 1050 | 0.0 | - |
202
+ | 0.8885 | 1100 | 0.0 | - |
203
+ | 0.9289 | 1150 | 0.0 | - |
204
+ | 0.9693 | 1200 | 0.0 | - |
205
+ | **1.0** | **1238** | **-** | **0.1555** |
206
+
207
+ * The bold row denotes the saved checkpoint.
208
+ ### Framework Versions
209
+ - Python: 3.10.11
210
+ - SetFit: 1.0.3
211
+ - Sentence Transformers: 2.5.1
212
+ - Transformers: 4.38.2
213
+ - PyTorch: 2.0.1
214
+ - Datasets: 2.18.0
215
+ - Tokenizers: 0.15.2
216
+
217
+ ## Citation
218
+
219
+ ### BibTeX
220
+ ```bibtex
221
+ @article{https://doi.org/10.48550/arxiv.2209.11055,
222
+ doi = {10.48550/ARXIV.2209.11055},
223
+ url = {https://arxiv.org/abs/2209.11055},
224
+ author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
225
+ keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
226
+ title = {Efficient Few-Shot Learning Without Prompts},
227
+ publisher = {arXiv},
228
+ year = {2022},
229
+ copyright = {Creative Commons Attribution 4.0 International}
230
+ }
231
+ ```
232
+
233
+ <!--
234
+ ## Glossary
235
+
236
+ *Clearly define terms in order to be accessible across audiences.*
237
+ -->
238
+
239
+ <!--
240
+ ## Model Card Authors
241
+
242
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
243
+ -->
244
+
245
+ <!--
246
+ ## Model Card Contact
247
+
248
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
249
+ -->
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "exp/Dune2Classifier/step_1238",
3
+ "architectures": [
4
+ "MPNetModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "mpnet",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 1,
20
+ "relative_attention_num_buckets": 32,
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.38.2",
23
+ "vocab_size": 30527
24
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "2.0.0",
4
+ "transformers": "4.7.0",
5
+ "pytorch": "1.9.0+cu102"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null
9
+ }
config_setfit.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "labels": [
3
+ "negative",
4
+ "positive"
5
+ ],
6
+ "normalize_embeddings": false
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02b256aa2e310b239aa4b3920a575c03fc53d075f1631e1edf214349d9789a7e
3
+ size 437967672
model_head.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:034f8755f06e904c8b226849b7d18e3df523dfbfd93710233551dc41e600eaeb
3
+ size 7640
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 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "104": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "30526": {
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
+ "do_basic_tokenize": true,
48
+ "do_lower_case": true,
49
+ "eos_token": "</s>",
50
+ "mask_token": "<mask>",
51
+ "max_length": 512,
52
+ "model_max_length": 512,
53
+ "never_split": null,
54
+ "pad_to_multiple_of": null,
55
+ "pad_token": "<pad>",
56
+ "pad_token_type_id": 0,
57
+ "padding_side": "right",
58
+ "sep_token": "</s>",
59
+ "stride": 0,
60
+ "strip_accents": null,
61
+ "tokenize_chinese_chars": true,
62
+ "tokenizer_class": "MPNetTokenizer",
63
+ "truncation_side": "right",
64
+ "truncation_strategy": "longest_first",
65
+ "unk_token": "[UNK]"
66
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff