vgarg commited on
Commit
463147e
1 Parent(s): 28b327b

Add SetFit model

Browse files
.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 +1,206 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: setfit
3
+ tags:
4
+ - setfit
5
+ - sentence-transformers
6
+ - text-classification
7
+ - generated_from_setfit_trainer
8
+ metrics:
9
+ - accuracy
10
+ widget:
11
+ - text: How does cannibalization within the RTEC category compare to other product
12
+ categories within the MT channel, influencing the overall volumelift?
13
+ - text: Can you identify the specific factors or challenges that contributed to the
14
+ decline in ROI within TT in 2022 compared to 2021?
15
+ - text: Which Sku cannibalizes higher margin Skus the most for CHEDRAUI channel_name?
16
+ - text: Can you compare the overall market share and competitive landscape of the
17
+ category more sensitive to internal cannibalization with other categories?
18
+ - text: Can you identify the key factors or challenges that have contributed to the
19
+ ROI decline within TT
20
+ pipeline_tag: text-classification
21
+ inference: true
22
+ base_model: intfloat/multilingual-e5-large
23
+ model-index:
24
+ - name: SetFit with intfloat/multilingual-e5-large
25
+ results:
26
+ - task:
27
+ type: text-classification
28
+ name: Text Classification
29
+ dataset:
30
+ name: Unknown
31
+ type: unknown
32
+ split: test
33
+ metrics:
34
+ - type: accuracy
35
+ value: 0.9130434782608695
36
+ name: Accuracy
37
+ ---
38
+
39
+ # SetFit with intfloat/multilingual-e5-large
40
+
41
+ This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [intfloat/multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
42
+
43
+ The model has been trained using an efficient few-shot learning technique that involves:
44
+
45
+ 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
46
+ 2. Training a classification head with features from the fine-tuned Sentence Transformer.
47
+
48
+ ## Model Details
49
+
50
+ ### Model Description
51
+ - **Model Type:** SetFit
52
+ - **Sentence Transformer body:** [intfloat/multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large)
53
+ - **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
54
+ - **Maximum Sequence Length:** 512 tokens
55
+ - **Number of Classes:** 3 classes
56
+ <!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
57
+ <!-- - **Language:** Unknown -->
58
+ <!-- - **License:** Unknown -->
59
+
60
+ ### Model Sources
61
+
62
+ - **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
63
+ - **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
64
+ - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
65
+
66
+ ### Model Labels
67
+ | Label | Examples |
68
+ |:------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
69
+ | 2 | <ul><li>'Are there particular factors or trends contributing to the high level of cannibalization for certain brands in the SS category?'</li><li>'How does the degree of cannibalization vary among different SKUs in the RTEC ?'</li><li>'Which Sku cannibalizes higher margin Skus the most?'</li></ul> |
70
+ | 1 | <ul><li>'Are there plans to enhance promotional activities specific to the MT to mitigate the ROI decline in 2023?'</li><li>'What are the main reasons for ROI decline in 2022 in MT compared to 2021?'</li><li>'Are there changes in consumer preferences or trends that have impacted the Lift of Zucaritas, and how does this compare to other brands like Pringles or Frutela?'</li></ul> |
71
+ | 0 | <ul><li>'What type of promotions worked best for MT Walmart in 2022?'</li><li>'Which channel has the max ROI and Vol Lift when we run the Promotion for RTEC category?'</li><li>'Which sub_catg_nm have the highest ROI in 2022?'</li></ul> |
72
+
73
+ ## Evaluation
74
+
75
+ ### Metrics
76
+ | Label | Accuracy |
77
+ |:--------|:---------|
78
+ | **all** | 0.9130 |
79
+
80
+ ## Uses
81
+
82
+ ### Direct Use for Inference
83
+
84
+ First install the SetFit library:
85
+
86
+ ```bash
87
+ pip install setfit
88
+ ```
89
+
90
+ Then you can load this model and run inference.
91
+
92
+ ```python
93
+ from setfit import SetFitModel
94
+
95
+ # Download from the 🤗 Hub
96
+ model = SetFitModel.from_pretrained("vgarg/promo_prescriptive_28_02_2024_v1")
97
+ # Run inference
98
+ preds = model("Which Sku cannibalizes higher margin Skus the most for CHEDRAUI channel_name?")
99
+ ```
100
+
101
+ <!--
102
+ ### Downstream Use
103
+
104
+ *List how someone could finetune this model on their own dataset.*
105
+ -->
106
+
107
+ <!--
108
+ ### Out-of-Scope Use
109
+
110
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
111
+ -->
112
+
113
+ <!--
114
+ ## Bias, Risks and Limitations
115
+
116
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
117
+ -->
118
+
119
+ <!--
120
+ ### Recommendations
121
+
122
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
123
+ -->
124
+
125
+ ## Training Details
126
+
127
+ ### Training Set Metrics
128
+ | Training set | Min | Median | Max |
129
+ |:-------------|:----|:--------|:----|
130
+ | Word count | 7 | 15.8333 | 30 |
131
+
132
+ | Label | Training Sample Count |
133
+ |:------|:----------------------|
134
+ | 0 | 10 |
135
+ | 1 | 10 |
136
+ | 2 | 10 |
137
+
138
+ ### Training Hyperparameters
139
+ - batch_size: (16, 16)
140
+ - num_epochs: (3, 3)
141
+ - max_steps: -1
142
+ - sampling_strategy: oversampling
143
+ - num_iterations: 20
144
+ - body_learning_rate: (2e-05, 2e-05)
145
+ - head_learning_rate: 2e-05
146
+ - loss: CosineSimilarityLoss
147
+ - distance_metric: cosine_distance
148
+ - margin: 0.25
149
+ - end_to_end: False
150
+ - use_amp: False
151
+ - warmup_proportion: 0.1
152
+ - seed: 42
153
+ - eval_max_steps: -1
154
+ - load_best_model_at_end: False
155
+
156
+ ### Training Results
157
+ | Epoch | Step | Training Loss | Validation Loss |
158
+ |:------:|:----:|:-------------:|:---------------:|
159
+ | 0.0133 | 1 | 0.3582 | - |
160
+ | 0.6667 | 50 | 0.0024 | - |
161
+ | 1.3333 | 100 | 0.0005 | - |
162
+ | 2.0 | 150 | 0.0004 | - |
163
+ | 2.6667 | 200 | 0.0002 | - |
164
+
165
+ ### Framework Versions
166
+ - Python: 3.10.12
167
+ - SetFit: 1.0.3
168
+ - Sentence Transformers: 2.4.0
169
+ - Transformers: 4.37.2
170
+ - PyTorch: 2.1.0+cu121
171
+ - Datasets: 2.17.1
172
+ - Tokenizers: 0.15.2
173
+
174
+ ## Citation
175
+
176
+ ### BibTeX
177
+ ```bibtex
178
+ @article{https://doi.org/10.48550/arxiv.2209.11055,
179
+ doi = {10.48550/ARXIV.2209.11055},
180
+ url = {https://arxiv.org/abs/2209.11055},
181
+ author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
182
+ keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
183
+ title = {Efficient Few-Shot Learning Without Prompts},
184
+ publisher = {arXiv},
185
+ year = {2022},
186
+ copyright = {Creative Commons Attribution 4.0 International}
187
+ }
188
+ ```
189
+
190
+ <!--
191
+ ## Glossary
192
+
193
+ *Clearly define terms in order to be accessible across audiences.*
194
+ -->
195
+
196
+ <!--
197
+ ## Model Card Authors
198
+
199
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
200
+ -->
201
+
202
+ <!--
203
+ ## Model Card Contact
204
+
205
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
206
+ -->
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": "4.37.2",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 250002
28
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "2.4.0",
4
+ "transformers": "4.37.2",
5
+ "pytorch": "2.1.0+cu121"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null
9
+ }
config_setfit.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "labels": null,
3
+ "normalize_embeddings": false
4
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d3bd170d8e549c5774c6f3418871cd2ccc3a6eaa23b3dab96e77e9caae2fc49
3
+ size 2239607176
model_head.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:997a2ea027de735616cea947590aedcabb2ad0a72a32169d93b8db838f186354
3
+ size 25471
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": 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:f1cc44ad7faaeec47241864835473fd5403f2da94673f3f764a77ebcb0a803ec
3
+ size 17083009
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
+ }