Commit From AutoTrain
Browse files- .gitattributes +3 -0
- README.md +52 -0
- config.json +80 -0
- pytorch_model.bin +3 -0
- sample_input.pkl +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -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 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags: autotrain
|
3 |
+
language: unk
|
4 |
+
widget:
|
5 |
+
- text: "I love AutoTrain 🤗"
|
6 |
+
datasets:
|
7 |
+
- Maxbnza/autotrain-data-address-training
|
8 |
+
co2_eq_emissions: 141.11976199388627
|
9 |
+
---
|
10 |
+
|
11 |
+
# Model Trained Using AutoTrain
|
12 |
+
|
13 |
+
- Problem type: Multi-class Classification
|
14 |
+
- Model ID: 1062136864
|
15 |
+
- CO2 Emissions (in grams): 141.11976199388627
|
16 |
+
|
17 |
+
## Validation Metrics
|
18 |
+
|
19 |
+
- Loss: 0.10147109627723694
|
20 |
+
- Accuracy: 0.9859325979151907
|
21 |
+
- Macro F1: 0.9715036017680622
|
22 |
+
- Micro F1: 0.9859325979151907
|
23 |
+
- Weighted F1: 0.9859070541468058
|
24 |
+
- Macro Precision: 0.9732956651937184
|
25 |
+
- Micro Precision: 0.9859325979151907
|
26 |
+
- Weighted Precision: 0.9860574596777458
|
27 |
+
- Macro Recall: 0.970199341807239
|
28 |
+
- Micro Recall: 0.9859325979151907
|
29 |
+
- Weighted Recall: 0.9859325979151907
|
30 |
+
|
31 |
+
|
32 |
+
## Usage
|
33 |
+
|
34 |
+
You can use cURL to access this model:
|
35 |
+
|
36 |
+
```
|
37 |
+
$ 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/Maxbnza/autotrain-address-training-1062136864
|
38 |
+
```
|
39 |
+
|
40 |
+
Or Python API:
|
41 |
+
|
42 |
+
```
|
43 |
+
from transformers import AutoModelForSequenceClassification, AutoTokenizer
|
44 |
+
|
45 |
+
model = AutoModelForSequenceClassification.from_pretrained("Maxbnza/autotrain-address-training-1062136864", use_auth_token=True)
|
46 |
+
|
47 |
+
tokenizer = AutoTokenizer.from_pretrained("Maxbnza/autotrain-address-training-1062136864", use_auth_token=True)
|
48 |
+
|
49 |
+
inputs = tokenizer("I love AutoTrain", return_tensors="pt")
|
50 |
+
|
51 |
+
outputs = model(**inputs)
|
52 |
+
```
|
config.json
ADDED
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "AutoTrain",
|
3 |
+
"_num_labels": 22,
|
4 |
+
"architectures": [
|
5 |
+
"XLMRobertaForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"classifier_dropout": null,
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 1024,
|
14 |
+
"id2label": {
|
15 |
+
"0": "Austria",
|
16 |
+
"1": "Belgium",
|
17 |
+
"2": "Denmark",
|
18 |
+
"3": "Finland",
|
19 |
+
"4": "France",
|
20 |
+
"5": "Germany",
|
21 |
+
"6": "Israel",
|
22 |
+
"7": "Italy",
|
23 |
+
"8": "Netherlands",
|
24 |
+
"9": "Norway",
|
25 |
+
"10": "Others",
|
26 |
+
"11": "Poland",
|
27 |
+
"12": "Portugal",
|
28 |
+
"13": "Saudi Arabia",
|
29 |
+
"14": "South Africa",
|
30 |
+
"15": "Spain",
|
31 |
+
"16": "Sweden",
|
32 |
+
"17": "Switzerland",
|
33 |
+
"18": "Turkey",
|
34 |
+
"19": "United Arab Emirates",
|
35 |
+
"20": "United Kingdom",
|
36 |
+
"21": "United States"
|
37 |
+
},
|
38 |
+
"initializer_range": 0.02,
|
39 |
+
"intermediate_size": 4096,
|
40 |
+
"label2id": {
|
41 |
+
"Austria": 0,
|
42 |
+
"Belgium": 1,
|
43 |
+
"Denmark": 2,
|
44 |
+
"Finland": 3,
|
45 |
+
"France": 4,
|
46 |
+
"Germany": 5,
|
47 |
+
"Israel": 6,
|
48 |
+
"Italy": 7,
|
49 |
+
"Netherlands": 8,
|
50 |
+
"Norway": 9,
|
51 |
+
"Others": 10,
|
52 |
+
"Poland": 11,
|
53 |
+
"Portugal": 12,
|
54 |
+
"Saudi Arabia": 13,
|
55 |
+
"South Africa": 14,
|
56 |
+
"Spain": 15,
|
57 |
+
"Sweden": 16,
|
58 |
+
"Switzerland": 17,
|
59 |
+
"Turkey": 18,
|
60 |
+
"United Arab Emirates": 19,
|
61 |
+
"United Kingdom": 20,
|
62 |
+
"United States": 21
|
63 |
+
},
|
64 |
+
"layer_norm_eps": 1e-05,
|
65 |
+
"max_length": 256,
|
66 |
+
"max_position_embeddings": 514,
|
67 |
+
"model_type": "xlm-roberta",
|
68 |
+
"num_attention_heads": 16,
|
69 |
+
"num_hidden_layers": 24,
|
70 |
+
"output_past": true,
|
71 |
+
"pad_token_id": 1,
|
72 |
+
"padding": "max_length",
|
73 |
+
"position_embedding_type": "absolute",
|
74 |
+
"problem_type": "single_label_classification",
|
75 |
+
"torch_dtype": "float32",
|
76 |
+
"transformers_version": "4.15.0",
|
77 |
+
"type_vocab_size": 1,
|
78 |
+
"use_cache": true,
|
79 |
+
"vocab_size": 250002
|
80 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65e01450449b5361ecade1e416c52b52bf2f1e5df2fa657caec4de169ad7a716
|
3 |
+
size 2239816045
|
sample_input.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66ebe240200ad3effb8826a0b0b297069888b133c17d2b19daa139f8d6a53171
|
3 |
+
size 5110
|
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 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "AutoTrain", "tokenizer_class": "XLMRobertaTokenizer"}
|