anudit commited on
Commit
970d786
·
verified ·
1 Parent(s): 7730653

Upload 7 files

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
+ pipeline.skops filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unknown
3
+ library_name: model2vec
4
+ license: mit
5
+ model_name: category_classifier
6
+ tags:
7
+ - embeddings
8
+ - static-embeddings
9
+ - sentence-transformers
10
+ ---
11
+
12
+ # category_classifier Model Card
13
+
14
+ This [Model2Vec](https://github.com/MinishLab/model2vec) model is a fine-tuned version of the [unknown](https://huggingface.co/unknown) Model2Vec model. It also includes a classifier head on top.
15
+
16
+ ## Installation
17
+
18
+ Install model2vec using pip:
19
+ ```
20
+ pip install model2vec[inference]
21
+ ```
22
+
23
+ ## Usage
24
+ Load this model using the `from_pretrained` method:
25
+ ```python
26
+ from model2vec.inference import StaticModelPipeline
27
+
28
+ # Load a pretrained Model2Vec model
29
+ model = StaticModelPipeline.from_pretrained("category_classifier")
30
+
31
+ # Predict labels
32
+ predicted = model.predict(["Example sentence"])
33
+ ```
34
+
35
+ ## Additional Resources
36
+
37
+ - [Model2Vec Repo](https://github.com/MinishLab/model2vec)
38
+ - [Model2Vec Base Models](https://huggingface.co/collections/minishlab/model2vec-base-models-66fd9dd9b7c3b3c0f25ca90e)
39
+ - [Model2Vec Results](https://github.com/MinishLab/model2vec/tree/main/results)
40
+ - [Model2Vec Tutorials](https://github.com/MinishLab/model2vec/tree/main/tutorials)
41
+ - [Website](https://minishlab.github.io/)
42
+
43
+ ## Library Authors
44
+
45
+ Model2Vec was developed by the [Minish Lab](https://github.com/MinishLab) team consisting of [Stephan Tulkens](https://github.com/stephantul) and [Thomas van Dongen](https://github.com/Pringled).
46
+
47
+ ## Citation
48
+
49
+ Please cite the [Model2Vec repository](https://github.com/MinishLab/model2vec) if you use this model in your work.
50
+ ```
51
+ @article{minishlab2024model2vec,
52
+ author = {Tulkens, Stephan and {van Dongen}, Thomas},
53
+ title = {Model2Vec: Fast State-of-the-Art Static Embeddings},
54
+ year = {2024},
55
+ url = {https://github.com/MinishLab/model2vec}
56
+ }
57
+ ```
category_mappings.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "category_to_idx": {
3
+ "earth_rejuvination": 0,
4
+ "efficient_movement": 1,
5
+ "energy": 2,
6
+ "food_agri": 3,
7
+ "governance": 4,
8
+ "human_health": 5,
9
+ "immersive": 6,
10
+ "impossible_problems": 7,
11
+ "intelligence": 8,
12
+ "machines_robotics": 9,
13
+ "neuro_tech": 10,
14
+ "quantum": 11,
15
+ "secure_digital_world": 12,
16
+ "space_exploration": 13
17
+ },
18
+ "idx_to_category": {
19
+ "0": "earth_rejuvination",
20
+ "1": "efficient_movement",
21
+ "2": "energy",
22
+ "3": "food_agri",
23
+ "4": "governance",
24
+ "5": "human_health",
25
+ "6": "immersive",
26
+ "7": "impossible_problems",
27
+ "8": "intelligence",
28
+ "9": "machines_robotics",
29
+ "10": "neuro_tech",
30
+ "11": "quantum",
31
+ "12": "secure_digital_world",
32
+ "13": "space_exploration"
33
+ },
34
+ "valid_categories": [
35
+ "neuro_tech",
36
+ "energy",
37
+ "secure_digital_world",
38
+ "earth_rejuvination",
39
+ "impossible_problems",
40
+ "intelligence",
41
+ "space_exploration",
42
+ "efficient_movement",
43
+ "quantum",
44
+ "human_health",
45
+ "governance",
46
+ "immersive",
47
+ "machines_robotics",
48
+ "food_agri"
49
+ ]
50
+ }
config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "normalize": true,
3
+ "embedding_dtype": "float32",
4
+ "vocabulary_quantization": 63091
5
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ba8db5fdbe43ceb57dfb9efaa5492d19aa6fbe38696a580774d99351ff1c9a1
3
+ size 129967700
modules.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": ".",
6
+ "type": "sentence_transformers.models.StaticEmbedding"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Normalize",
12
+ "type": "sentence_transformers.models.Normalize"
13
+ }
14
+ ]
pipeline.skops ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95c768fe88e947bebdab82724d8caa194bbb1cfe5f5aaf4bb76b3205615f54cb
3
+ size 7625703
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff