Commit From AutoTrain
Browse files- .gitattributes +3 -0
- README.md +45 -0
- config.json +35 -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
@@ -25,3 +25,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
29 |
+
*.tar.gz filter=lfs diff=lfs merge=lfs -text
|
30 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags: autotrain
|
3 |
+
language: en
|
4 |
+
widget:
|
5 |
+
- text: "I love AutoTrain 🤗"
|
6 |
+
datasets:
|
7 |
+
- ismail-lucifer011/autotrain-data-company_all
|
8 |
+
co2_eq_emissions: 0.848790823793881
|
9 |
+
---
|
10 |
+
|
11 |
+
# Model Trained Using AutoTrain
|
12 |
+
|
13 |
+
- Problem type: Entity Extraction
|
14 |
+
- Model ID: 903429548
|
15 |
+
- CO2 Emissions (in grams): 0.848790823793881
|
16 |
+
|
17 |
+
## Validation Metrics
|
18 |
+
|
19 |
+
- Loss: 0.006148040760308504
|
20 |
+
- Accuracy: 0.9979930566588805
|
21 |
+
- Precision: 0.9814944904963571
|
22 |
+
- Recall: 0.9817210885036588
|
23 |
+
- F1: 0.9816077764228254
|
24 |
+
|
25 |
+
## Usage
|
26 |
+
|
27 |
+
You can use cURL to access this model:
|
28 |
+
|
29 |
+
```
|
30 |
+
$ 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/ismail-lucifer011/autotrain-company_all-903429548
|
31 |
+
```
|
32 |
+
|
33 |
+
Or Python API:
|
34 |
+
|
35 |
+
```
|
36 |
+
from transformers import AutoModelForTokenClassification, AutoTokenizer
|
37 |
+
|
38 |
+
model = AutoModelForTokenClassification.from_pretrained("ismail-lucifer011/autotrain-company_all-903429548", use_auth_token=True)
|
39 |
+
|
40 |
+
tokenizer = AutoTokenizer.from_pretrained("ismail-lucifer011/autotrain-company_all-903429548", use_auth_token=True)
|
41 |
+
|
42 |
+
inputs = tokenizer("I love AutoTrain", return_tensors="pt")
|
43 |
+
|
44 |
+
outputs = model(**inputs)
|
45 |
+
```
|
config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "AutoTrain",
|
3 |
+
"_num_labels": 2,
|
4 |
+
"activation": "gelu",
|
5 |
+
"architectures": [
|
6 |
+
"DistilBertForTokenClassification"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.1,
|
9 |
+
"dim": 768,
|
10 |
+
"dropout": 0.1,
|
11 |
+
"hidden_dim": 3072,
|
12 |
+
"id2label": {
|
13 |
+
"0": "Company",
|
14 |
+
"1": "OOV"
|
15 |
+
},
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"label2id": {
|
18 |
+
"Company": 0,
|
19 |
+
"OOV": 1
|
20 |
+
},
|
21 |
+
"max_length": 128,
|
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 |
+
"qa_dropout": 0.1,
|
29 |
+
"seq_classif_dropout": 0.2,
|
30 |
+
"sinusoidal_pos_embds": false,
|
31 |
+
"tie_weights_": true,
|
32 |
+
"torch_dtype": "float32",
|
33 |
+
"transformers_version": "4.15.0",
|
34 |
+
"vocab_size": 30522
|
35 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08dc2aeca786b6dbd530de235f7a39166bc1e2e8ea7608e0438b263d741f7731
|
3 |
+
size 265497077
|
sample_input.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4295bde9084014334166e7f75a1318f389479ff7e11578528bd95ed1b40d36a1
|
3 |
+
size 4936
|
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": true, "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": "AutoTrain", "tokenizer_class": "DistilBertTokenizer"}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|