Instructions to use MKChong/smart-invoice-processor-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MKChong/smart-invoice-processor-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="MKChong/smart-invoice-processor-v1")# Load model directly from transformers import AutoProcessor, AutoModelForTokenClassification processor = AutoProcessor.from_pretrained("MKChong/smart-invoice-processor-v1") model = AutoModelForTokenClassification.from_pretrained("MKChong/smart-invoice-processor-v1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update with own trained weights for version 4
Browse files- config.json +56 -41
- model.safetensors +2 -2
- tokenizer.json +16 -2
- tokenizer_config.json +1 -1
config.json
CHANGED
|
@@ -15,55 +15,71 @@
|
|
| 15 |
"hidden_size": 768,
|
| 16 |
"id2label": {
|
| 17 |
"0": "O",
|
| 18 |
-
"1": "B-
|
| 19 |
-
"2": "I-
|
| 20 |
-
"3": "B-
|
| 21 |
-
"4": "I-
|
| 22 |
-
"5": "B-
|
| 23 |
-
"6": "I-
|
| 24 |
-
"7": "B-
|
| 25 |
-
"8": "I-
|
| 26 |
-
"9": "B-
|
| 27 |
-
"10": "I-
|
| 28 |
-
"11": "B-
|
| 29 |
-
"12": "I-
|
| 30 |
-
"13": "B-
|
| 31 |
-
"14": "I-
|
| 32 |
-
"15": "B-
|
| 33 |
-
"16": "I-
|
| 34 |
"17": "B-TAX",
|
| 35 |
"18": "I-TAX",
|
| 36 |
-
"19": "B-
|
| 37 |
-
"20": "I-
|
| 38 |
-
"21": "B-
|
| 39 |
-
"22": "I-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
},
|
| 41 |
"initializer_range": 0.02,
|
| 42 |
"input_size": 224,
|
| 43 |
"intermediate_size": 3072,
|
| 44 |
"label2id": {
|
| 45 |
-
"B-
|
| 46 |
-
"B-
|
| 47 |
-
"B-
|
| 48 |
-
"B-
|
| 49 |
-
"B-
|
| 50 |
-
"B-
|
| 51 |
-
"B-
|
| 52 |
-
"B-
|
| 53 |
-
"B-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 54 |
"B-TAX": 17,
|
| 55 |
-
"B-TOTAL":
|
| 56 |
-
"I-
|
| 57 |
-
"I-
|
| 58 |
-
"I-
|
| 59 |
-
"I-
|
| 60 |
-
"I-
|
| 61 |
-
"I-
|
| 62 |
-
"I-
|
| 63 |
-
"I-
|
| 64 |
-
"I-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 65 |
"I-TAX": 18,
|
| 66 |
-
"I-TOTAL":
|
| 67 |
"O": 0
|
| 68 |
},
|
| 69 |
"layer_norm_eps": 1e-05,
|
|
@@ -84,7 +100,6 @@
|
|
| 84 |
"text_embed": true,
|
| 85 |
"transformers_version": "5.3.0",
|
| 86 |
"type_vocab_size": 1,
|
| 87 |
-
"use_cache": false,
|
| 88 |
"visual_embed": true,
|
| 89 |
"vocab_size": 50265
|
| 90 |
}
|
|
|
|
| 15 |
"hidden_size": 768,
|
| 16 |
"id2label": {
|
| 17 |
"0": "O",
|
| 18 |
+
"1": "B-INVOICE_NO",
|
| 19 |
+
"2": "I-INVOICE_NO",
|
| 20 |
+
"3": "B-DATE",
|
| 21 |
+
"4": "I-DATE",
|
| 22 |
+
"5": "B-CURRENCY",
|
| 23 |
+
"6": "I-CURRENCY",
|
| 24 |
+
"7": "B-SELLER_NAME",
|
| 25 |
+
"8": "I-SELLER_NAME",
|
| 26 |
+
"9": "B-SELLER_ADDRESS",
|
| 27 |
+
"10": "I-SELLER_ADDRESS",
|
| 28 |
+
"11": "B-BUYER_NAME",
|
| 29 |
+
"12": "I-BUYER_NAME",
|
| 30 |
+
"13": "B-BUYER_ADDRESS",
|
| 31 |
+
"14": "I-BUYER_ADDRESS",
|
| 32 |
+
"15": "B-TOTAL",
|
| 33 |
+
"16": "I-TOTAL",
|
| 34 |
"17": "B-TAX",
|
| 35 |
"18": "I-TAX",
|
| 36 |
+
"19": "B-ITEM_DESC",
|
| 37 |
+
"20": "I-ITEM_DESC",
|
| 38 |
+
"21": "B-ITEM_QTY",
|
| 39 |
+
"22": "I-ITEM_QTY",
|
| 40 |
+
"23": "B-ITEM_PRICE",
|
| 41 |
+
"24": "I-ITEM_PRICE",
|
| 42 |
+
"25": "B-ITEM_TOTAL",
|
| 43 |
+
"26": "I-ITEM_TOTAL",
|
| 44 |
+
"27": "B-BANK_NAME",
|
| 45 |
+
"28": "I-BANK_NAME",
|
| 46 |
+
"29": "B-BANK_ACCT",
|
| 47 |
+
"30": "I-BANK_ACCT"
|
| 48 |
},
|
| 49 |
"initializer_range": 0.02,
|
| 50 |
"input_size": 224,
|
| 51 |
"intermediate_size": 3072,
|
| 52 |
"label2id": {
|
| 53 |
+
"B-BANK_ACCT": 29,
|
| 54 |
+
"B-BANK_NAME": 27,
|
| 55 |
+
"B-BUYER_ADDRESS": 13,
|
| 56 |
+
"B-BUYER_NAME": 11,
|
| 57 |
+
"B-CURRENCY": 5,
|
| 58 |
+
"B-DATE": 3,
|
| 59 |
+
"B-INVOICE_NO": 1,
|
| 60 |
+
"B-ITEM_DESC": 19,
|
| 61 |
+
"B-ITEM_PRICE": 23,
|
| 62 |
+
"B-ITEM_QTY": 21,
|
| 63 |
+
"B-ITEM_TOTAL": 25,
|
| 64 |
+
"B-SELLER_ADDRESS": 9,
|
| 65 |
+
"B-SELLER_NAME": 7,
|
| 66 |
"B-TAX": 17,
|
| 67 |
+
"B-TOTAL": 15,
|
| 68 |
+
"I-BANK_ACCT": 30,
|
| 69 |
+
"I-BANK_NAME": 28,
|
| 70 |
+
"I-BUYER_ADDRESS": 14,
|
| 71 |
+
"I-BUYER_NAME": 12,
|
| 72 |
+
"I-CURRENCY": 6,
|
| 73 |
+
"I-DATE": 4,
|
| 74 |
+
"I-INVOICE_NO": 2,
|
| 75 |
+
"I-ITEM_DESC": 20,
|
| 76 |
+
"I-ITEM_PRICE": 24,
|
| 77 |
+
"I-ITEM_QTY": 22,
|
| 78 |
+
"I-ITEM_TOTAL": 26,
|
| 79 |
+
"I-SELLER_ADDRESS": 10,
|
| 80 |
+
"I-SELLER_NAME": 8,
|
| 81 |
"I-TAX": 18,
|
| 82 |
+
"I-TOTAL": 16,
|
| 83 |
"O": 0
|
| 84 |
},
|
| 85 |
"layer_norm_eps": 1e-05,
|
|
|
|
| 100 |
"text_embed": true,
|
| 101 |
"transformers_version": "5.3.0",
|
| 102 |
"type_vocab_size": 1,
|
|
|
|
| 103 |
"visual_embed": true,
|
| 104 |
"vocab_size": 50265
|
| 105 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e78b3ccef6fc6c9d2dc8c45f4ae3b20c40594d60cc45d9a4bd12f744a98d98c
|
| 3 |
+
size 503791932
|
tokenizer.json
CHANGED
|
@@ -1,7 +1,21 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": {
|
| 4 |
+
"direction": "Right",
|
| 5 |
+
"max_length": 512,
|
| 6 |
+
"strategy": "LongestFirst",
|
| 7 |
+
"stride": 0
|
| 8 |
+
},
|
| 9 |
+
"padding": {
|
| 10 |
+
"strategy": {
|
| 11 |
+
"Fixed": 512
|
| 12 |
+
},
|
| 13 |
+
"direction": "Right",
|
| 14 |
+
"pad_to_multiple_of": null,
|
| 15 |
+
"pad_id": 1,
|
| 16 |
+
"pad_type_id": 0,
|
| 17 |
+
"pad_token": "<pad>"
|
| 18 |
+
},
|
| 19 |
"added_tokens": [
|
| 20 |
{
|
| 21 |
"id": 0,
|
tokenizer_config.json
CHANGED
|
@@ -12,7 +12,7 @@
|
|
| 12 |
],
|
| 13 |
"eos_token": "</s>",
|
| 14 |
"errors": "replace",
|
| 15 |
-
"is_local":
|
| 16 |
"mask_token": "<mask>",
|
| 17 |
"model_max_length": 512,
|
| 18 |
"only_label_first_subword": true,
|
|
|
|
| 12 |
],
|
| 13 |
"eos_token": "</s>",
|
| 14 |
"errors": "replace",
|
| 15 |
+
"is_local": true,
|
| 16 |
"mask_token": "<mask>",
|
| 17 |
"model_max_length": 512,
|
| 18 |
"only_label_first_subword": true,
|