Commit From AutoNLP
Browse files- .gitattributes +2 -0
- README.md +50 -0
- config.json +114 -0
- pytorch_model.bin +3 -0
- sample_input.pkl +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
.gitattributes
CHANGED
@@ -15,3 +15,5 @@
|
|
15 |
*.pt filter=lfs diff=lfs merge=lfs -text
|
16 |
*.pth filter=lfs diff=lfs merge=lfs -text
|
17 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
15 |
*.pt filter=lfs diff=lfs merge=lfs -text
|
16 |
*.pth filter=lfs diff=lfs merge=lfs -text
|
17 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
18 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
19 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags: autonlp
|
3 |
+
language: en
|
4 |
+
widget:
|
5 |
+
- text: "I love AutoNLP 🤗"
|
6 |
+
datasets:
|
7 |
+
- idrimadrid/autonlp-data-creator_classifications
|
8 |
+
---
|
9 |
+
|
10 |
+
# Model Trained Using AutoNLP
|
11 |
+
|
12 |
+
- Problem type: Multi-class Classification
|
13 |
+
- Model ID: 4021083
|
14 |
+
|
15 |
+
## Validation Metrics
|
16 |
+
|
17 |
+
- Loss: 0.6848716735839844
|
18 |
+
- Accuracy: 0.8825910931174089
|
19 |
+
- Macro F1: 0.41301646762109634
|
20 |
+
- Micro F1: 0.8825910931174088
|
21 |
+
- Weighted F1: 0.863740586166105
|
22 |
+
- Macro Precision: 0.4129337301330573
|
23 |
+
- Micro Precision: 0.8825910931174089
|
24 |
+
- Weighted Precision: 0.8531335941587811
|
25 |
+
- Macro Recall: 0.44466614072309585
|
26 |
+
- Micro Recall: 0.8825910931174089
|
27 |
+
- Weighted Recall: 0.8825910931174089
|
28 |
+
|
29 |
+
|
30 |
+
## Usage
|
31 |
+
|
32 |
+
You can use cURL to access this model:
|
33 |
+
|
34 |
+
```
|
35 |
+
$ curl -X POST -H "Authorization: Bearer YOUR_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "I love AutoNLP"}' https://api-inference.huggingface.co/models/idrimadrid/autonlp-creator_classifications-4021083
|
36 |
+
```
|
37 |
+
|
38 |
+
Or Python API:
|
39 |
+
|
40 |
+
```
|
41 |
+
from transformers import AutoModelForSequenceClassification, AutoTokenizer
|
42 |
+
|
43 |
+
model = AutoModelForSequenceClassification.from_pretrained("idrimadrid/autonlp-creator_classifications-4021083", use_auth_token=True)
|
44 |
+
|
45 |
+
tokenizer = AutoTokenizer.from_pretrained("idrimadrid/autonlp-creator_classifications-4021083", use_auth_token=True)
|
46 |
+
|
47 |
+
inputs = tokenizer("I love AutoNLP", return_tensors="pt")
|
48 |
+
|
49 |
+
outputs = model(**inputs)
|
50 |
+
```
|
config.json
ADDED
@@ -0,0 +1,114 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "AutoNLP",
|
3 |
+
"_num_labels": 41,
|
4 |
+
"architectures": [
|
5 |
+
"BertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "ABC Studios",
|
14 |
+
"1": "Blizzard Entertainment",
|
15 |
+
"2": "Capcom",
|
16 |
+
"3": "Cartoon Network",
|
17 |
+
"4": "Clive Barker",
|
18 |
+
"5": "DC Comics",
|
19 |
+
"6": "Dark Horse Comics",
|
20 |
+
"7": "Disney",
|
21 |
+
"8": "Dreamworks",
|
22 |
+
"9": "George Lucas",
|
23 |
+
"10": "George R. R. Martin",
|
24 |
+
"11": "Hanna-Barbera",
|
25 |
+
"12": "HarperCollins",
|
26 |
+
"13": "Hasbro",
|
27 |
+
"14": "IDW Publishing",
|
28 |
+
"15": "Ian Fleming",
|
29 |
+
"16": "Icon Comics",
|
30 |
+
"17": "Image Comics",
|
31 |
+
"18": "J. K. Rowling",
|
32 |
+
"19": "J. R. R. Tolkien",
|
33 |
+
"20": "Konami",
|
34 |
+
"21": "Lego",
|
35 |
+
"22": "Marvel Comics",
|
36 |
+
"23": "Matt Groening",
|
37 |
+
"24": "Mattel",
|
38 |
+
"25": "Microsoft",
|
39 |
+
"26": "Mortal Kombat",
|
40 |
+
"27": "NBC - Heroes",
|
41 |
+
"28": "Namco",
|
42 |
+
"29": "Nintendo",
|
43 |
+
"30": "Sega",
|
44 |
+
"31": "Shueisha",
|
45 |
+
"32": "Sony Pictures",
|
46 |
+
"33": "South Park",
|
47 |
+
"34": "Star Trek",
|
48 |
+
"35": "Stephen King",
|
49 |
+
"36": "SyFy",
|
50 |
+
"37": "Team Epic TV",
|
51 |
+
"38": "Ubisoft",
|
52 |
+
"39": "Universal Studios",
|
53 |
+
"40": "Wildstorm"
|
54 |
+
},
|
55 |
+
"initializer_range": 0.02,
|
56 |
+
"intermediate_size": 3072,
|
57 |
+
"label2id": {
|
58 |
+
"ABC Studios": 0,
|
59 |
+
"Blizzard Entertainment": 1,
|
60 |
+
"Capcom": 2,
|
61 |
+
"Cartoon Network": 3,
|
62 |
+
"Clive Barker": 4,
|
63 |
+
"DC Comics": 5,
|
64 |
+
"Dark Horse Comics": 6,
|
65 |
+
"Disney": 7,
|
66 |
+
"Dreamworks": 8,
|
67 |
+
"George Lucas": 9,
|
68 |
+
"George R. R. Martin": 10,
|
69 |
+
"Hanna-Barbera": 11,
|
70 |
+
"HarperCollins": 12,
|
71 |
+
"Hasbro": 13,
|
72 |
+
"IDW Publishing": 14,
|
73 |
+
"Ian Fleming": 15,
|
74 |
+
"Icon Comics": 16,
|
75 |
+
"Image Comics": 17,
|
76 |
+
"J. K. Rowling": 18,
|
77 |
+
"J. R. R. Tolkien": 19,
|
78 |
+
"Konami": 20,
|
79 |
+
"Lego": 21,
|
80 |
+
"Marvel Comics": 22,
|
81 |
+
"Matt Groening": 23,
|
82 |
+
"Mattel": 24,
|
83 |
+
"Microsoft": 25,
|
84 |
+
"Mortal Kombat": 26,
|
85 |
+
"NBC - Heroes": 27,
|
86 |
+
"Namco": 28,
|
87 |
+
"Nintendo": 29,
|
88 |
+
"Sega": 30,
|
89 |
+
"Shueisha": 31,
|
90 |
+
"Sony Pictures": 32,
|
91 |
+
"South Park": 33,
|
92 |
+
"Star Trek": 34,
|
93 |
+
"Stephen King": 35,
|
94 |
+
"SyFy": 36,
|
95 |
+
"Team Epic TV": 37,
|
96 |
+
"Ubisoft": 38,
|
97 |
+
"Universal Studios": 39,
|
98 |
+
"Wildstorm": 40
|
99 |
+
},
|
100 |
+
"layer_norm_eps": 1e-12,
|
101 |
+
"max_length": 512,
|
102 |
+
"max_position_embeddings": 512,
|
103 |
+
"model_type": "bert",
|
104 |
+
"num_attention_heads": 12,
|
105 |
+
"num_hidden_layers": 12,
|
106 |
+
"pad_token_id": 0,
|
107 |
+
"padding": "max_length",
|
108 |
+
"position_embedding_type": "absolute",
|
109 |
+
"problem_type": "single_label_classification",
|
110 |
+
"transformers_version": "4.8.0",
|
111 |
+
"type_vocab_size": 2,
|
112 |
+
"use_cache": true,
|
113 |
+
"vocab_size": 28996
|
114 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d366c5a73f3a78347d21f487ddbc95d42dc779172601d80b0ebc6d364a0385e
|
3 |
+
size 433451309
|
sample_input.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6349a2e0e11e30bef5bf47e9269ce9bafbb53c08625deb81c9a31697237e743f
|
3 |
+
size 13606
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "AutoNLP", "tokenizer_class": "BertTokenizer"}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|