Commit From AutoTrain
Browse files- .gitattributes +3 -0
- README.md +49 -0
- config.json +61 -0
- model.safetensors +3 -0
- pytorch_model.bin +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +19 -0
- tokenizer.json +3 -0
- tokenizer_config.json +24 -0
.gitattributes
CHANGED
@@ -33,3 +33,6 @@ 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 |
+
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
37 |
+
*.tar.gz filter=lfs diff=lfs merge=lfs -text
|
38 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- autotrain
|
4 |
+
- token-classification
|
5 |
+
language:
|
6 |
+
- fr
|
7 |
+
widget:
|
8 |
+
- text: "I love AutoTrain"
|
9 |
+
datasets:
|
10 |
+
- davanstrien/autotrain-data-french-ner-blank-model
|
11 |
+
co2_eq_emissions:
|
12 |
+
emissions: 0.11647938304211661
|
13 |
+
---
|
14 |
+
|
15 |
+
# Model Trained Using AutoTrain
|
16 |
+
|
17 |
+
- Problem type: Entity Extraction
|
18 |
+
- Model ID: 69856137957
|
19 |
+
- CO2 Emissions (in grams): 0.1165
|
20 |
+
|
21 |
+
## Validation Metrics
|
22 |
+
|
23 |
+
- Loss: 1.510
|
24 |
+
- Accuracy: 0.706
|
25 |
+
- Precision: 0.648
|
26 |
+
- Recall: 0.679
|
27 |
+
- F1: 0.663
|
28 |
+
|
29 |
+
## Usage
|
30 |
+
|
31 |
+
You can use cURL to access this model:
|
32 |
+
|
33 |
+
```
|
34 |
+
$ 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/davanstrien/autotrain-french-ner-blank-model-69856137957
|
35 |
+
```
|
36 |
+
|
37 |
+
Or Python API:
|
38 |
+
|
39 |
+
```
|
40 |
+
from transformers import AutoModelForTokenClassification, AutoTokenizer
|
41 |
+
|
42 |
+
model = AutoModelForTokenClassification.from_pretrained("davanstrien/autotrain-french-ner-blank-model-69856137957", use_auth_token=True)
|
43 |
+
|
44 |
+
tokenizer = AutoTokenizer.from_pretrained("davanstrien/autotrain-french-ner-blank-model-69856137957", use_auth_token=True)
|
45 |
+
|
46 |
+
inputs = tokenizer("I love AutoTrain", return_tensors="pt")
|
47 |
+
|
48 |
+
outputs = model(**inputs)
|
49 |
+
```
|
config.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "AutoTrain",
|
3 |
+
"_num_labels": 13,
|
4 |
+
"architectures": [
|
5 |
+
"CamembertForTokenClassification"
|
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": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "B-Dosage",
|
16 |
+
"1": "B-Drug",
|
17 |
+
"2": "B-Duration",
|
18 |
+
"3": "B-Form",
|
19 |
+
"4": "B-Frequency",
|
20 |
+
"5": "B-Strength",
|
21 |
+
"6": "I-Dosage",
|
22 |
+
"7": "I-Drug",
|
23 |
+
"8": "I-Duration",
|
24 |
+
"9": "I-Form",
|
25 |
+
"10": "I-Frequency",
|
26 |
+
"11": "I-Strength",
|
27 |
+
"12": "O"
|
28 |
+
},
|
29 |
+
"initializer_range": 0.02,
|
30 |
+
"intermediate_size": 3072,
|
31 |
+
"label2id": {
|
32 |
+
"B-Dosage": 0,
|
33 |
+
"B-Drug": 1,
|
34 |
+
"B-Duration": 2,
|
35 |
+
"B-Form": 3,
|
36 |
+
"B-Frequency": 4,
|
37 |
+
"B-Strength": 5,
|
38 |
+
"I-Dosage": 6,
|
39 |
+
"I-Drug": 7,
|
40 |
+
"I-Duration": 8,
|
41 |
+
"I-Form": 9,
|
42 |
+
"I-Frequency": 10,
|
43 |
+
"I-Strength": 11,
|
44 |
+
"O": 12
|
45 |
+
},
|
46 |
+
"layer_norm_eps": 1e-05,
|
47 |
+
"max_length": 64,
|
48 |
+
"max_position_embeddings": 514,
|
49 |
+
"model_type": "camembert",
|
50 |
+
"num_attention_heads": 12,
|
51 |
+
"num_hidden_layers": 12,
|
52 |
+
"output_past": true,
|
53 |
+
"pad_token_id": 1,
|
54 |
+
"padding": "max_length",
|
55 |
+
"position_embedding_type": "absolute",
|
56 |
+
"torch_dtype": "float32",
|
57 |
+
"transformers_version": "4.29.2",
|
58 |
+
"type_vocab_size": 1,
|
59 |
+
"use_cache": true,
|
60 |
+
"vocab_size": 32005
|
61 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15b266bf5a475ee55411cd07e48eabd99b5becc3e793cfb74fa66df4350fbc81
|
3 |
+
size 440193556
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb31f4c20267fc7c380ea79d8521136871807f002dc18fc798c57ac9c83f9813
|
3 |
+
size 440238125
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f98f266fdc548c94216aaadc13ffaaafacf0c8793303e2195322d954549ea261
|
3 |
+
size 808767
|
special_tokens_map.json
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<s>NOTUSED",
|
4 |
+
"</s>NOTUSED"
|
5 |
+
],
|
6 |
+
"bos_token": "<s>",
|
7 |
+
"cls_token": "<s>",
|
8 |
+
"eos_token": "</s>",
|
9 |
+
"mask_token": {
|
10 |
+
"content": "<mask>",
|
11 |
+
"lstrip": true,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<pad>",
|
17 |
+
"sep_token": "</s>",
|
18 |
+
"unk_token": "<unk>"
|
19 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa7ba9e8280c5c6df7e9e224dde795adc6a9d56df77d869093dbb97b3698bb8c
|
3 |
+
size 2418785
|
tokenizer_config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<s>NOTUSED",
|
4 |
+
"</s>NOTUSED"
|
5 |
+
],
|
6 |
+
"bos_token": "<s>",
|
7 |
+
"clean_up_tokenization_spaces": true,
|
8 |
+
"cls_token": "<s>",
|
9 |
+
"eos_token": "</s>",
|
10 |
+
"mask_token": {
|
11 |
+
"__type": "AddedToken",
|
12 |
+
"content": "<mask>",
|
13 |
+
"lstrip": true,
|
14 |
+
"normalized": true,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false
|
17 |
+
},
|
18 |
+
"model_max_length": 1000000000000000019884624838656,
|
19 |
+
"pad_token": "<pad>",
|
20 |
+
"sep_token": "</s>",
|
21 |
+
"sp_model_kwargs": {},
|
22 |
+
"tokenizer_class": "CamembertTokenizer",
|
23 |
+
"unk_token": "<unk>"
|
24 |
+
}
|