Commit
•
a3ee03b
1
Parent(s):
c9cbca3
Update model files
Browse files- config.json +55 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +18 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "l3cube-pune/marathi-topic-long",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"embedding_size": 768,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "Auto",
|
| 14 |
+
"1": "Bhakti",
|
| 15 |
+
"2": "Crime",
|
| 16 |
+
"3": "Education",
|
| 17 |
+
"4": "Fashion",
|
| 18 |
+
"5": "Health",
|
| 19 |
+
"6": "International",
|
| 20 |
+
"7": "Manoranjan",
|
| 21 |
+
"8": "Politics",
|
| 22 |
+
"9": "Sports",
|
| 23 |
+
"10": "Tech",
|
| 24 |
+
"11": "Travel"
|
| 25 |
+
},
|
| 26 |
+
"initializer_range": 0.02,
|
| 27 |
+
"intermediate_size": 3072,
|
| 28 |
+
"label2id": {
|
| 29 |
+
"Auto": 0,
|
| 30 |
+
"Bhakti": 1,
|
| 31 |
+
"Crime": 2,
|
| 32 |
+
"Education": 3,
|
| 33 |
+
"Fashion": 4,
|
| 34 |
+
"Health": 5,
|
| 35 |
+
"International": 6,
|
| 36 |
+
"Manoranjan": 7,
|
| 37 |
+
"Politics": 8,
|
| 38 |
+
"Sports": 9,
|
| 39 |
+
"Tech": 10,
|
| 40 |
+
"Travel": 11
|
| 41 |
+
},
|
| 42 |
+
"layer_norm_eps": 1e-12,
|
| 43 |
+
"max_position_embeddings": 512,
|
| 44 |
+
"model_type": "bert",
|
| 45 |
+
"num_attention_heads": 12,
|
| 46 |
+
"num_hidden_layers": 12,
|
| 47 |
+
"pad_token_id": 0,
|
| 48 |
+
"position_embedding_type": "absolute",
|
| 49 |
+
"problem_type": "single_label_classification",
|
| 50 |
+
"torch_dtype": "float32",
|
| 51 |
+
"transformers_version": "4.22.0",
|
| 52 |
+
"type_vocab_size": 2,
|
| 53 |
+
"use_cache": true,
|
| 54 |
+
"vocab_size": 197285
|
| 55 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:77df2dd375fe57751b2a1c9eb7bc9206ee0eb1c728959b2652bf3b5b57110517
|
| 3 |
+
size 950331765
|
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 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"clean_up_tokenization_spaces": true,
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_basic_tokenize": true,
|
| 5 |
+
"do_lower_case": false,
|
| 6 |
+
"lowercase": false,
|
| 7 |
+
"mask_token": "[MASK]",
|
| 8 |
+
"model_max_length": 512,
|
| 9 |
+
"name_or_path": "l3cube-pune/marathi-topic-long",
|
| 10 |
+
"never_split": null,
|
| 11 |
+
"pad_token": "[PAD]",
|
| 12 |
+
"sep_token": "[SEP]",
|
| 13 |
+
"special_tokens_map_file": "l3cube-pune/marathi-topic-long/special_tokens_map.json",
|
| 14 |
+
"strip_accents": false,
|
| 15 |
+
"tokenize_chinese_chars": true,
|
| 16 |
+
"tokenizer_class": "BertTokenizer",
|
| 17 |
+
"unk_token": "[UNK]"
|
| 18 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|