albertosei commited on
Commit
6e08d8a
·
verified ·
1 Parent(s): 93d004c

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "dim": 768,
8
+ "dropout": 0.1,
9
+ "hidden_dim": 3072,
10
+ "id2label": {
11
+ "0": "Credit Note",
12
+ "1": "Debit Note",
13
+ "2": "Invoice",
14
+ "3": "Purchase Order",
15
+ "4": "Receipt"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "label2id": {
19
+ "Credit Note": 0,
20
+ "Debit Note": 1,
21
+ "Invoice": 2,
22
+ "Purchase Order": 3,
23
+ "Receipt": 4
24
+ },
25
+ "max_position_embeddings": 512,
26
+ "model_type": "distilbert",
27
+ "n_heads": 12,
28
+ "n_layers": 6,
29
+ "pad_token_id": 0,
30
+ "problem_type": "single_label_classification",
31
+ "qa_dropout": 0.1,
32
+ "seq_classif_dropout": 0.2,
33
+ "sinusoidal_pos_embds": false,
34
+ "tie_weights_": true,
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.52.4",
37
+ "vocab_size": 30522
38
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24c61b11e45999d382e2c155167a57e5c9d36872f51bf5a514450b520ca38547
3
+ size 267841796
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "max_length": 512,
50
+ "model_max_length": 512,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "stride": 0,
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "DistilBertTokenizer",
57
+ "truncation_side": "right",
58
+ "truncation_strategy": "longest_first",
59
+ "unk_token": "[UNK]"
60
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e255ccac95e3d5ac3fb73947fe29fcd74497849b315dbbfbd3e08f3285e4ff3
3
+ size 5368
upload_model1.py ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # upload_model.py
2
+ from huggingface_hub import HfApi, HfFolder
3
+
4
+ # Define your model path and the desired repository ID on the Hub
5
+ MODEL_PATH = r"C:\Users\alber\OneDrive\Desktop\PROJECTS\TYNCAD\distilbert" # Path to your local model folder
6
+ REPO_ID = "albertosei/distilbert_classdoc" #
7
+
8
+ print(f"Uploading model from '{MODEL_PATH}' to '{REPO_ID}'...")
9
+
10
+ # The library will automatically find and use the token you just saved.
11
+ api = HfApi()
12
+
13
+ # Create the repository on the Hub if it doesn't exist
14
+ api.create_repo(repo_id=REPO_ID, repo_type="model", exist_ok=True)
15
+
16
+ # Upload the entire folder
17
+ api.upload_folder(
18
+ folder_path=MODEL_PATH,
19
+ repo_id=REPO_ID,
20
+ repo_type="model",
21
+ )
22
+
23
+ print("✅ Upload complete! Check your model on the Hugging Face Hub.")
vocab.txt ADDED
The diff for this file is too large to render. See raw diff