Instructions to use LovenOO/BERT_large_without_preprocessing with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use LovenOO/BERT_large_without_preprocessing with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="LovenOO/BERT_large_without_preprocessing")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("LovenOO/BERT_large_without_preprocessing") model = AutoModelForSequenceClassification.from_pretrained("LovenOO/BERT_large_without_preprocessing") - Notebooks
- Google Colab
- Kaggle
Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +47 -0
- pytorch_model.bin +3 -0
- runs/Aug14_19-14-19_e8c619643c0d/events.out.tfevents.1692040470.e8c619643c0d.665.0 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +13 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
checkpoint-*/
|
config.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bert-large-uncased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "Population and Society",
|
| 14 |
+
"1": "Children Education and Skills",
|
| 15 |
+
"2": "Labour Market and Welfare",
|
| 16 |
+
"3": "Health and Social Care",
|
| 17 |
+
"4": "Crime and Security",
|
| 18 |
+
"5": "Transport Environment and Climate Change",
|
| 19 |
+
"6": "Economy",
|
| 20 |
+
"7": "Housing Planning and Local Services"
|
| 21 |
+
},
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"intermediate_size": 4096,
|
| 24 |
+
"label2id": {
|
| 25 |
+
"Children Education and Skills": 1,
|
| 26 |
+
"Crime and Security": 4,
|
| 27 |
+
"Economy": 6,
|
| 28 |
+
"Health and Social Care": 3,
|
| 29 |
+
"Housing Planning and Local Services": 7,
|
| 30 |
+
"Labour Market and Welfare": 2,
|
| 31 |
+
"Population and Society": 0,
|
| 32 |
+
"Transport Environment and Climate Change": 5
|
| 33 |
+
},
|
| 34 |
+
"layer_norm_eps": 1e-12,
|
| 35 |
+
"max_position_embeddings": 512,
|
| 36 |
+
"model_type": "bert",
|
| 37 |
+
"num_attention_heads": 16,
|
| 38 |
+
"num_hidden_layers": 24,
|
| 39 |
+
"pad_token_id": 0,
|
| 40 |
+
"position_embedding_type": "absolute",
|
| 41 |
+
"problem_type": "single_label_classification",
|
| 42 |
+
"torch_dtype": "float32",
|
| 43 |
+
"transformers_version": "4.31.0",
|
| 44 |
+
"type_vocab_size": 2,
|
| 45 |
+
"use_cache": true,
|
| 46 |
+
"vocab_size": 30522
|
| 47 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0038b52ec4799b9f2cd247c0c932dc62b4d1b16e059f8752df2f62bc05ad1d00
|
| 3 |
+
size 1340734769
|
runs/Aug14_19-14-19_e8c619643c0d/events.out.tfevents.1692040470.e8c619643c0d.665.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0db820ab64b25d739960b2d0be74190a187ebc002a3802bd6af71c6e53252255
|
| 3 |
+
size 5348
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"clean_up_tokenization_spaces": true,
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_lower_case": true,
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"model_max_length": 512,
|
| 7 |
+
"pad_token": "[PAD]",
|
| 8 |
+
"sep_token": "[SEP]",
|
| 9 |
+
"strip_accents": null,
|
| 10 |
+
"tokenize_chinese_chars": true,
|
| 11 |
+
"tokenizer_class": "BertTokenizer",
|
| 12 |
+
"unk_token": "[UNK]"
|
| 13 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd85ee63574a0c9a9b71436b5615694719d90ef97d1d640b8c9c17ca6013a9c0
|
| 3 |
+
size 4027
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|