Upload 7 files
Browse files- README.md +56 -0
- config.json +112 -0
- pytorch_model.bin +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +19 -0
- tokenizer.json +0 -0
- tokenizer_config.json +24 -0
README.md
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- autotrain
|
4 |
+
- text-classification
|
5 |
+
language:
|
6 |
+
- fr
|
7 |
+
widget:
|
8 |
+
- text: "I love AutoTrain 🤗"
|
9 |
+
datasets:
|
10 |
+
- huynhdoo/autotrain-data-jva-activity-classification
|
11 |
+
co2_eq_emissions:
|
12 |
+
emissions: 12.734050517307358
|
13 |
+
---
|
14 |
+
|
15 |
+
# Model Trained Using AutoTrain
|
16 |
+
|
17 |
+
- Problem type: Multi-class Classification
|
18 |
+
- Model ID: 2096367492
|
19 |
+
- CO2 Emissions (in grams): 12.7341
|
20 |
+
|
21 |
+
## Validation Metrics
|
22 |
+
|
23 |
+
- Loss: 0.888
|
24 |
+
- Accuracy: 0.812
|
25 |
+
- Macro F1: 0.684
|
26 |
+
- Micro F1: 0.812
|
27 |
+
- Weighted F1: 0.808
|
28 |
+
- Macro Precision: 0.708
|
29 |
+
- Micro Precision: 0.812
|
30 |
+
- Weighted Precision: 0.813
|
31 |
+
- Macro Recall: 0.691
|
32 |
+
- Micro Recall: 0.812
|
33 |
+
- Weighted Recall: 0.812
|
34 |
+
|
35 |
+
|
36 |
+
## Usage
|
37 |
+
|
38 |
+
You can use cURL to access this model:
|
39 |
+
|
40 |
+
```
|
41 |
+
$ 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/huynhdoo/autotrain-jva-activity-classification-2096367492
|
42 |
+
```
|
43 |
+
|
44 |
+
Or Python API:
|
45 |
+
|
46 |
+
```
|
47 |
+
from transformers import AutoModelForSequenceClassification, AutoTokenizer
|
48 |
+
|
49 |
+
model = AutoModelForSequenceClassification.from_pretrained("huynhdoo/autotrain-jva-activity-classification-2096367492", use_auth_token=True)
|
50 |
+
|
51 |
+
tokenizer = AutoTokenizer.from_pretrained("huynhdoo/autotrain-jva-activity-classification-2096367492", use_auth_token=True)
|
52 |
+
|
53 |
+
inputs = tokenizer("I love AutoTrain", return_tensors="pt")
|
54 |
+
|
55 |
+
outputs = model(**inputs)
|
56 |
+
```
|
config.json
ADDED
@@ -0,0 +1,112 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "AutoTrain",
|
3 |
+
"_num_labels": 38,
|
4 |
+
"architectures": [
|
5 |
+
"CamembertForSequenceClassification"
|
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": "Accompagnement aux activit\u00e9s sportives",
|
16 |
+
"1": "Accompagnement \u00e0 la mobilit\u00e9",
|
17 |
+
"2": "Accueil / Information",
|
18 |
+
"3": "Actions de sensibilisation",
|
19 |
+
"4": "Aide aux d\u00e9marches administratives",
|
20 |
+
"5": "Alphab\u00e9tisation / Apprentissage du fran\u00e7ais (FLE)",
|
21 |
+
"6": "Am\u00e9nagement d'espaces naturels",
|
22 |
+
"7": "Animation / Loisirs",
|
23 |
+
"8": "Collecte de fonds",
|
24 |
+
"9": "Collecte de produits",
|
25 |
+
"10": "Communication",
|
26 |
+
"11": "Dialogue interculturel",
|
27 |
+
"12": "Distribution",
|
28 |
+
"13": "Droit et conseil juridique",
|
29 |
+
"14": "Gestion administrative",
|
30 |
+
"15": "Gestion de projets",
|
31 |
+
"16": "Gestion des ressources humaines",
|
32 |
+
"17": "Gestion financi\u00e8re / comptabilit\u00e9",
|
33 |
+
"18": "Gouvernance",
|
34 |
+
"19": "Informatique",
|
35 |
+
"20": "Logistique",
|
36 |
+
"21": "Lutte contre l'isolement",
|
37 |
+
"22": "Maraude",
|
38 |
+
"23": "Mentorat & Parrainage",
|
39 |
+
"24": "M\u00e9diation culturelle",
|
40 |
+
"25": "M\u00e9dical",
|
41 |
+
"26": "Ramassage de d\u00e9chets",
|
42 |
+
"27": "Recherche de partenariats",
|
43 |
+
"28": "Secourisme et s\u00e9curit\u00e9 civile",
|
44 |
+
"29": "Services \u00e0 la personne",
|
45 |
+
"30": "Soins aux animaux",
|
46 |
+
"31": "Soutien scolaire et formation",
|
47 |
+
"32": "Traduction",
|
48 |
+
"33": "Travaux manuels",
|
49 |
+
"34": "Valorisation du patrimoine",
|
50 |
+
"35": "Vie citoyenne",
|
51 |
+
"36": "\u00c9coute / Aide psychologique",
|
52 |
+
"37": "\u00c9v\u00e9nementiel"
|
53 |
+
},
|
54 |
+
"initializer_range": 0.02,
|
55 |
+
"intermediate_size": 3072,
|
56 |
+
"label2id": {
|
57 |
+
"Accompagnement aux activit\u00e9s sportives": 0,
|
58 |
+
"Accompagnement \u00e0 la mobilit\u00e9": 1,
|
59 |
+
"Accueil / Information": 2,
|
60 |
+
"Actions de sensibilisation": 3,
|
61 |
+
"Aide aux d\u00e9marches administratives": 4,
|
62 |
+
"Alphab\u00e9tisation / Apprentissage du fran\u00e7ais (FLE)": 5,
|
63 |
+
"Am\u00e9nagement d'espaces naturels": 6,
|
64 |
+
"Animation / Loisirs": 7,
|
65 |
+
"Collecte de fonds": 8,
|
66 |
+
"Collecte de produits": 9,
|
67 |
+
"Communication": 10,
|
68 |
+
"Dialogue interculturel": 11,
|
69 |
+
"Distribution": 12,
|
70 |
+
"Droit et conseil juridique": 13,
|
71 |
+
"Gestion administrative": 14,
|
72 |
+
"Gestion de projets": 15,
|
73 |
+
"Gestion des ressources humaines": 16,
|
74 |
+
"Gestion financi\u00e8re / comptabilit\u00e9": 17,
|
75 |
+
"Gouvernance": 18,
|
76 |
+
"Informatique": 19,
|
77 |
+
"Logistique": 20,
|
78 |
+
"Lutte contre l'isolement": 21,
|
79 |
+
"Maraude": 22,
|
80 |
+
"Mentorat & Parrainage": 23,
|
81 |
+
"M\u00e9diation culturelle": 24,
|
82 |
+
"M\u00e9dical": 25,
|
83 |
+
"Ramassage de d\u00e9chets": 26,
|
84 |
+
"Recherche de partenariats": 27,
|
85 |
+
"Secourisme et s\u00e9curit\u00e9 civile": 28,
|
86 |
+
"Services \u00e0 la personne": 29,
|
87 |
+
"Soins aux animaux": 30,
|
88 |
+
"Soutien scolaire et formation": 31,
|
89 |
+
"Traduction": 32,
|
90 |
+
"Travaux manuels": 33,
|
91 |
+
"Valorisation du patrimoine": 34,
|
92 |
+
"Vie citoyenne": 35,
|
93 |
+
"\u00c9coute / Aide psychologique": 36,
|
94 |
+
"\u00c9v\u00e9nementiel": 37
|
95 |
+
},
|
96 |
+
"layer_norm_eps": 1e-05,
|
97 |
+
"max_length": 256,
|
98 |
+
"max_position_embeddings": 514,
|
99 |
+
"model_type": "camembert",
|
100 |
+
"num_attention_heads": 12,
|
101 |
+
"num_hidden_layers": 12,
|
102 |
+
"output_past": true,
|
103 |
+
"pad_token_id": 1,
|
104 |
+
"padding": "max_length",
|
105 |
+
"position_embedding_type": "absolute",
|
106 |
+
"problem_type": "single_label_classification",
|
107 |
+
"torch_dtype": "float32",
|
108 |
+
"transformers_version": "4.22.1",
|
109 |
+
"type_vocab_size": 1,
|
110 |
+
"use_cache": true,
|
111 |
+
"vocab_size": 32005
|
112 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82c9565bbc6056502acbcb02d2caf8c215595ea12150c2ae1f780ad59d8cdf97
|
3 |
+
size 442676333
|
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
The diff for this file is too large to render.
See raw diff
|
|
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 |
+
"cls_token": "<s>",
|
8 |
+
"eos_token": "</s>",
|
9 |
+
"mask_token": {
|
10 |
+
"__type": "AddedToken",
|
11 |
+
"content": "<mask>",
|
12 |
+
"lstrip": true,
|
13 |
+
"normalized": true,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
},
|
17 |
+
"name_or_path": "AutoTrain",
|
18 |
+
"pad_token": "<pad>",
|
19 |
+
"sep_token": "</s>",
|
20 |
+
"sp_model_kwargs": {},
|
21 |
+
"special_tokens_map_file": null,
|
22 |
+
"tokenizer_class": "CamembertTokenizer",
|
23 |
+
"unk_token": "<unk>"
|
24 |
+
}
|