Commit From AutoTrain
Browse files- .gitattributes +2 -0
- README.md +50 -0
- config.json +36 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +14 -0
- vocab.txt +0 -0
.gitattributes
CHANGED
@@ -29,3 +29,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
29 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
30 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
31 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
29 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
30 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
31 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
32 |
+
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
33 |
+
*.tar.gz filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- autotrain
|
4 |
+
- text-classification
|
5 |
+
language:
|
6 |
+
- unk
|
7 |
+
widget:
|
8 |
+
- text: "I love AutoTrain 🤗"
|
9 |
+
datasets:
|
10 |
+
- sasha/autotrain-data-DistilBERT-imdb
|
11 |
+
co2_eq_emissions:
|
12 |
+
emissions: 0.04687419137564709
|
13 |
+
---
|
14 |
+
|
15 |
+
# Model Trained Using AutoTrain
|
16 |
+
|
17 |
+
- Problem type: Binary Classification
|
18 |
+
- Model ID: 1275448782
|
19 |
+
- CO2 Emissions (in grams): 0.0469
|
20 |
+
|
21 |
+
## Validation Metrics
|
22 |
+
|
23 |
+
- Loss: 0.256
|
24 |
+
- Accuracy: 0.900
|
25 |
+
- Precision: 0.891
|
26 |
+
- Recall: 0.913
|
27 |
+
- AUC: 0.965
|
28 |
+
- F1: 0.902
|
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 AutoTrain"}' https://api-inference.huggingface.co/models/sasha/autotrain-DistilBERT-imdb-1275448782
|
36 |
+
```
|
37 |
+
|
38 |
+
Or Python API:
|
39 |
+
|
40 |
+
```
|
41 |
+
from transformers import AutoModelForSequenceClassification, AutoTokenizer
|
42 |
+
|
43 |
+
model = AutoModelForSequenceClassification.from_pretrained("sasha/autotrain-DistilBERT-imdb-1275448782", use_auth_token=True)
|
44 |
+
|
45 |
+
tokenizer = AutoTokenizer.from_pretrained("sasha/autotrain-DistilBERT-imdb-1275448782", use_auth_token=True)
|
46 |
+
|
47 |
+
inputs = tokenizer("I love AutoTrain", return_tensors="pt")
|
48 |
+
|
49 |
+
outputs = model(**inputs)
|
50 |
+
```
|
config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "AutoTrain",
|
3 |
+
"_num_labels": 2,
|
4 |
+
"activation": "gelu",
|
5 |
+
"architectures": [
|
6 |
+
"DistilBertForSequenceClassification"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.1,
|
9 |
+
"dim": 768,
|
10 |
+
"dropout": 0.1,
|
11 |
+
"hidden_dim": 3072,
|
12 |
+
"id2label": {
|
13 |
+
"0": "neg",
|
14 |
+
"1": "pos"
|
15 |
+
},
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"label2id": {
|
18 |
+
"neg": 0,
|
19 |
+
"pos": 1
|
20 |
+
},
|
21 |
+
"max_length": 192,
|
22 |
+
"max_position_embeddings": 512,
|
23 |
+
"model_type": "distilbert",
|
24 |
+
"n_heads": 12,
|
25 |
+
"n_layers": 6,
|
26 |
+
"pad_token_id": 0,
|
27 |
+
"padding": "max_length",
|
28 |
+
"problem_type": "single_label_classification",
|
29 |
+
"qa_dropout": 0.1,
|
30 |
+
"seq_classif_dropout": 0.2,
|
31 |
+
"sinusoidal_pos_embds": false,
|
32 |
+
"tie_weights_": true,
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.20.0",
|
35 |
+
"vocab_size": 30522
|
36 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7daff1809e982d7eb22a398c34929635378ac6bd6e3a706a685bd5a7723fb3ea
|
3 |
+
size 267854321
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_lower_case": true,
|
4 |
+
"mask_token": "[MASK]",
|
5 |
+
"model_max_length": 512,
|
6 |
+
"name_or_path": "AutoTrain",
|
7 |
+
"pad_token": "[PAD]",
|
8 |
+
"sep_token": "[SEP]",
|
9 |
+
"special_tokens_map_file": null,
|
10 |
+
"strip_accents": null,
|
11 |
+
"tokenize_chinese_chars": true,
|
12 |
+
"tokenizer_class": "DistilBertTokenizer",
|
13 |
+
"unk_token": "[UNK]"
|
14 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|