First version of the your-model-name model and tokenizer.
Browse files- config.json +49 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"SC_weighted_BERT"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"bos_token_id": null,
|
7 |
+
"do_sample": false,
|
8 |
+
"eos_token_ids": null,
|
9 |
+
"finetuning_task": null,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "hate speech",
|
15 |
+
"1": "normal",
|
16 |
+
"2": "offensive"
|
17 |
+
},
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 3072,
|
20 |
+
"is_decoder": false,
|
21 |
+
"label2id": {
|
22 |
+
"hate speech": 0,
|
23 |
+
"normal": 1,
|
24 |
+
"offensive":2
|
25 |
+
},
|
26 |
+
"layer_norm_eps": 1e-12,
|
27 |
+
"length_penalty": 1.0,
|
28 |
+
"max_length": 20,
|
29 |
+
"max_position_embeddings": 512,
|
30 |
+
"model_type": "bert",
|
31 |
+
"num_attention_heads": 12,
|
32 |
+
"num_beams": 1,
|
33 |
+
"num_hidden_layers": 12,
|
34 |
+
"num_labels": 3,
|
35 |
+
"num_return_sequences": 1,
|
36 |
+
"output_attentions": true,
|
37 |
+
"output_hidden_states": false,
|
38 |
+
"output_past": true,
|
39 |
+
"pad_token_id": 0,
|
40 |
+
"pruned_heads": {},
|
41 |
+
"repetition_penalty": 1.0,
|
42 |
+
"temperature": 1.0,
|
43 |
+
"top_k": 50,
|
44 |
+
"top_p": 1.0,
|
45 |
+
"torchscript": false,
|
46 |
+
"type_vocab_size": 2,
|
47 |
+
"use_bfloat16": false,
|
48 |
+
"vocab_size": 30522
|
49 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7939d499f5c2ec887db9c09d9e790f33321686a4993c6b3da7d89db059a7452e
|
3 |
+
size 437988463
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "max_len": 512}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|