dannymartin
commited on
Commit
•
6134b7e
1
Parent(s):
4b4ae69
Add SetFit model
Browse files- 1_Pooling/config.json +3 -3
- README.md +32 -12
- config.json +12 -19
- config_setfit.json +2 -2
- model.safetensors +2 -2
- model_head.pkl +2 -2
- modules.json +0 -6
- sentence_bert_config.json +1 -1
- special_tokens_map.json +19 -5
- tokenizer.json +0 -0
- tokenizer_config.json +17 -22
- vocab.txt +5 -0
1_Pooling/config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
-
"word_embedding_dimension":
|
3 |
-
"pooling_mode_cls_token":
|
4 |
-
"pooling_mode_mean_tokens":
|
5 |
"pooling_mode_max_tokens": false,
|
6 |
"pooling_mode_mean_sqrt_len_tokens": false,
|
7 |
"pooling_mode_weightedmean_tokens": false,
|
|
|
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,
|
README.md
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
---
|
2 |
-
base_model:
|
3 |
library_name: setfit
|
4 |
metrics:
|
5 |
- accuracy
|
@@ -164,11 +164,25 @@ widget:
|
|
164 |
|
165 |
'
|
166 |
inference: false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
167 |
---
|
168 |
|
169 |
-
# SetFit with
|
170 |
|
171 |
-
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [
|
172 |
|
173 |
The model has been trained using an efficient few-shot learning technique that involves:
|
174 |
|
@@ -179,7 +193,7 @@ The model has been trained using an efficient few-shot learning technique that i
|
|
179 |
|
180 |
### Model Description
|
181 |
- **Model Type:** SetFit
|
182 |
-
- **Sentence Transformer body:** [
|
183 |
- **Classification head:** a OneVsRestClassifier instance
|
184 |
- **Maximum Sequence Length:** 512 tokens
|
185 |
- **Number of Classes:** 13 classes
|
@@ -193,6 +207,13 @@ The model has been trained using an efficient few-shot learning technique that i
|
|
193 |
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
|
194 |
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
|
195 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
196 |
## Uses
|
197 |
|
198 |
### Direct Use for Inference
|
@@ -251,8 +272,8 @@ Add water and seasonings. Bring to a boil. Cover and simmer on low for 20 minu
|
|
251 |
| Word count | 4 | 4.2308 | 5 |
|
252 |
|
253 |
### Training Hyperparameters
|
254 |
-
- batch_size: (
|
255 |
-
- num_epochs: (1,
|
256 |
- max_steps: -1
|
257 |
- sampling_strategy: oversampling
|
258 |
- body_learning_rate: (2e-05, 1e-05)
|
@@ -265,15 +286,14 @@ Add water and seasonings. Bring to a boil. Cover and simmer on low for 20 minu
|
|
265 |
- warmup_proportion: 0.1
|
266 |
- seed: 42
|
267 |
- eval_max_steps: -1
|
268 |
-
- load_best_model_at_end:
|
269 |
|
270 |
### Training Results
|
271 |
-
| Epoch
|
272 |
-
|
273 |
-
| 0.
|
274 |
-
|
|
275 |
|
276 |
-
* The bold row denotes the saved checkpoint.
|
277 |
### Framework Versions
|
278 |
- Python: 3.10.12
|
279 |
- SetFit: 1.0.3
|
|
|
1 |
---
|
2 |
+
base_model: sentence-transformers/paraphrase-mpnet-base-v2
|
3 |
library_name: setfit
|
4 |
metrics:
|
5 |
- accuracy
|
|
|
164 |
|
165 |
'
|
166 |
inference: false
|
167 |
+
model-index:
|
168 |
+
- name: SetFit with sentence-transformers/paraphrase-mpnet-base-v2
|
169 |
+
results:
|
170 |
+
- task:
|
171 |
+
type: text-classification
|
172 |
+
name: Text Classification
|
173 |
+
dataset:
|
174 |
+
name: Unknown
|
175 |
+
type: unknown
|
176 |
+
split: test
|
177 |
+
metrics:
|
178 |
+
- type: accuracy
|
179 |
+
value: 0.0
|
180 |
+
name: Accuracy
|
181 |
---
|
182 |
|
183 |
+
# SetFit with sentence-transformers/paraphrase-mpnet-base-v2
|
184 |
|
185 |
+
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 OneVsRestClassifier instance is used for classification.
|
186 |
|
187 |
The model has been trained using an efficient few-shot learning technique that involves:
|
188 |
|
|
|
193 |
|
194 |
### Model Description
|
195 |
- **Model Type:** SetFit
|
196 |
+
- **Sentence Transformer body:** [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2)
|
197 |
- **Classification head:** a OneVsRestClassifier instance
|
198 |
- **Maximum Sequence Length:** 512 tokens
|
199 |
- **Number of Classes:** 13 classes
|
|
|
207 |
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
|
208 |
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
|
209 |
|
210 |
+
## Evaluation
|
211 |
+
|
212 |
+
### Metrics
|
213 |
+
| Label | Accuracy |
|
214 |
+
|:--------|:---------|
|
215 |
+
| **all** | 0.0 |
|
216 |
+
|
217 |
## Uses
|
218 |
|
219 |
### Direct Use for Inference
|
|
|
272 |
| Word count | 4 | 4.2308 | 5 |
|
273 |
|
274 |
### Training Hyperparameters
|
275 |
+
- batch_size: (16, 2)
|
276 |
+
- num_epochs: (1, 16)
|
277 |
- max_steps: -1
|
278 |
- sampling_strategy: oversampling
|
279 |
- body_learning_rate: (2e-05, 1e-05)
|
|
|
286 |
- warmup_proportion: 0.1
|
287 |
- seed: 42
|
288 |
- eval_max_steps: -1
|
289 |
+
- load_best_model_at_end: False
|
290 |
|
291 |
### Training Results
|
292 |
+
| Epoch | Step | Training Loss | Validation Loss |
|
293 |
+
|:------:|:----:|:-------------:|:---------------:|
|
294 |
+
| 0.0256 | 1 | 0.1572 | - |
|
295 |
+
| 1.0 | 39 | 0.0152 | 0.2304 |
|
296 |
|
|
|
297 |
### Framework Versions
|
298 |
- Python: 3.10.12
|
299 |
- SetFit: 1.0.3
|
config.json
CHANGED
@@ -1,31 +1,24 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
-
"
|
|
|
8 |
"hidden_act": "gelu",
|
9 |
"hidden_dropout_prob": 0.1,
|
10 |
-
"hidden_size":
|
11 |
-
"id2label": {
|
12 |
-
"0": "LABEL_0"
|
13 |
-
},
|
14 |
"initializer_range": 0.02,
|
15 |
-
"intermediate_size":
|
16 |
-
"
|
17 |
-
|
18 |
-
|
19 |
-
"layer_norm_eps": 1e-12,
|
20 |
-
"max_position_embeddings": 512,
|
21 |
-
"model_type": "bert",
|
22 |
"num_attention_heads": 12,
|
23 |
"num_hidden_layers": 12,
|
24 |
-
"pad_token_id":
|
25 |
-
"
|
26 |
"torch_dtype": "float32",
|
27 |
"transformers_version": "4.42.3",
|
28 |
-
"
|
29 |
-
"use_cache": true,
|
30 |
-
"vocab_size": 30522
|
31 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "sentence-transformers/paraphrase-mpnet-base-v2",
|
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": "4.42.3",
|
23 |
+
"vocab_size": 30527
|
|
|
|
|
24 |
}
|
config_setfit.json
CHANGED
@@ -1,4 +1,5 @@
|
|
1 |
{
|
|
|
2 |
"labels": [
|
3 |
"Baking",
|
4 |
"Grilling",
|
@@ -13,6 +14,5 @@
|
|
13 |
"Saut\u00e9ing",
|
14 |
"Sous vide",
|
15 |
"Stir-frying"
|
16 |
-
]
|
17 |
-
"normalize_embeddings": false
|
18 |
}
|
|
|
1 |
{
|
2 |
+
"normalize_embeddings": false,
|
3 |
"labels": [
|
4 |
"Baking",
|
5 |
"Grilling",
|
|
|
14 |
"Saut\u00e9ing",
|
15 |
"Sous vide",
|
16 |
"Stir-frying"
|
17 |
+
]
|
|
|
18 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c459619a48663c3e77b088e66e942b68a15128aae191f8f0aec44d930d28c54
|
3 |
+
size 437967672
|
model_head.pkl
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fadf9efa1bf6b64e594a679094b02e3ab341007efaeb88e8bca7ed5499a49a0e
|
3 |
+
size 85252
|
modules.json
CHANGED
@@ -10,11 +10,5 @@
|
|
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 |
]
|
|
|
10 |
"name": "1",
|
11 |
"path": "1_Pooling",
|
12 |
"type": "sentence_transformers.models.Pooling"
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
}
|
14 |
]
|
sentence_bert_config.json
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
{
|
2 |
"max_seq_length": 512,
|
3 |
-
"do_lower_case":
|
4 |
}
|
|
|
1 |
{
|
2 |
"max_seq_length": 512,
|
3 |
+
"do_lower_case": false
|
4 |
}
|
special_tokens_map.json
CHANGED
@@ -1,27 +1,41 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"cls_token": {
|
3 |
-
"content": "
|
4 |
"lstrip": false,
|
5 |
"normalized": false,
|
6 |
"rstrip": false,
|
7 |
"single_word": false
|
8 |
},
|
9 |
-
"
|
10 |
-
"content": "
|
11 |
"lstrip": false,
|
12 |
"normalized": false,
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
"pad_token": {
|
17 |
-
"content": "
|
18 |
"lstrip": false,
|
19 |
"normalized": false,
|
20 |
"rstrip": false,
|
21 |
"single_word": false
|
22 |
},
|
23 |
"sep_token": {
|
24 |
-
"content": "
|
25 |
"lstrip": false,
|
26 |
"normalized": false,
|
27 |
"rstrip": false,
|
|
|
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,
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,64 +1,59 @@
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
-
"content": "
|
5 |
"lstrip": false,
|
6 |
"normalized": false,
|
7 |
"rstrip": false,
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
-
"
|
12 |
-
"content": "
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
15 |
"rstrip": false,
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
-
"
|
20 |
-
"content": "
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
-
"
|
28 |
-
"content": "[
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
},
|
35 |
-
"
|
36 |
-
"content": "
|
37 |
-
"lstrip":
|
38 |
"normalized": false,
|
39 |
"rstrip": false,
|
40 |
"single_word": false,
|
41 |
"special": true
|
42 |
}
|
43 |
},
|
|
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
-
"cls_token": "
|
46 |
"do_basic_tokenize": true,
|
47 |
"do_lower_case": true,
|
48 |
-
"
|
49 |
-
"
|
50 |
"model_max_length": 512,
|
51 |
"never_split": null,
|
52 |
-
"
|
53 |
-
"
|
54 |
-
"pad_token_type_id": 0,
|
55 |
-
"padding_side": "right",
|
56 |
-
"sep_token": "[SEP]",
|
57 |
-
"stride": 0,
|
58 |
"strip_accents": null,
|
59 |
"tokenize_chinese_chars": true,
|
60 |
-
"tokenizer_class": "
|
61 |
-
"truncation_side": "right",
|
62 |
-
"truncation_strategy": "longest_first",
|
63 |
"unk_token": "[UNK]"
|
64 |
}
|
|
|
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 |
"model_max_length": 512,
|
52 |
"never_split": null,
|
53 |
+
"pad_token": "<pad>",
|
54 |
+
"sep_token": "</s>",
|
|
|
|
|
|
|
|
|
55 |
"strip_accents": null,
|
56 |
"tokenize_chinese_chars": true,
|
57 |
+
"tokenizer_class": "MPNetTokenizer",
|
|
|
|
|
58 |
"unk_token": "[UNK]"
|
59 |
}
|
vocab.txt
CHANGED
@@ -1,3 +1,7 @@
|
|
|
|
|
|
|
|
|
|
1 |
[PAD]
|
2 |
[unused0]
|
3 |
[unused1]
|
@@ -30520,3 +30524,4 @@ necessitated
|
|
30520 |
##:
|
30521 |
##?
|
30522 |
##~
|
|
|
|
1 |
+
<s>
|
2 |
+
<pad>
|
3 |
+
</s>
|
4 |
+
<unk>
|
5 |
[PAD]
|
6 |
[unused0]
|
7 |
[unused1]
|
|
|
30524 |
##:
|
30525 |
##?
|
30526 |
##~
|
30527 |
+
<mask>
|