pdelobelle
commited on
Commit
·
afb9830
1
Parent(s):
ea1e1e0
Add RobBERT model for NER
Browse files- config.json +69 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_num_labels": 9,
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bad_words_ids": null,
|
8 |
+
"bos_token_id": null,
|
9 |
+
"decoder_start_token_id": null,
|
10 |
+
"do_sample": false,
|
11 |
+
"early_stopping": false,
|
12 |
+
"eos_token_id": null,
|
13 |
+
"finetuning_task": null,
|
14 |
+
"hidden_act": "gelu",
|
15 |
+
"hidden_dropout_prob": 0.1,
|
16 |
+
"hidden_size": 768,
|
17 |
+
"id2label": {
|
18 |
+
"0": "B-PER",
|
19 |
+
"1": "B-ORG",
|
20 |
+
"2": "B-LOC",
|
21 |
+
"3": "B-MISC",
|
22 |
+
"4": "I-PER",
|
23 |
+
"5": "I-ORG",
|
24 |
+
"6": "I-LOC",
|
25 |
+
"7": "I-MISC",
|
26 |
+
"8": "O"
|
27 |
+
},
|
28 |
+
"initializer_range": 0.02,
|
29 |
+
"intermediate_size": 3072,
|
30 |
+
"is_decoder": false,
|
31 |
+
"is_encoder_decoder": false,
|
32 |
+
"label2id": {
|
33 |
+
"B-LOC": 2,
|
34 |
+
"B-MISC": 3,
|
35 |
+
"B-ORG": 1,
|
36 |
+
"B-PER": 0,
|
37 |
+
"I-LOC": 6,
|
38 |
+
"I-MISC": 7,
|
39 |
+
"I-ORG": 5,
|
40 |
+
"I-PER": 4,
|
41 |
+
"O": 8
|
42 |
+
},
|
43 |
+
"layer_norm_eps": 1e-05,
|
44 |
+
"length_penalty": 1.0,
|
45 |
+
"max_length": 20,
|
46 |
+
"max_position_embeddings": 514,
|
47 |
+
"min_length": 0,
|
48 |
+
"model_type": "roberta",
|
49 |
+
"no_repeat_ngram_size": 0,
|
50 |
+
"num_attention_heads": 12,
|
51 |
+
"num_beams": 1,
|
52 |
+
"num_hidden_layers": 12,
|
53 |
+
"num_return_sequences": 1,
|
54 |
+
"output_attentions": false,
|
55 |
+
"output_hidden_states": false,
|
56 |
+
"output_past": true,
|
57 |
+
"pad_token_id": 0,
|
58 |
+
"prefix": null,
|
59 |
+
"pruned_heads": {},
|
60 |
+
"repetition_penalty": 1.0,
|
61 |
+
"task_specific_params": null,
|
62 |
+
"temperature": 1.0,
|
63 |
+
"top_k": 50,
|
64 |
+
"top_p": 1.0,
|
65 |
+
"torchscript": false,
|
66 |
+
"type_vocab_size": 1,
|
67 |
+
"use_bfloat16": false,
|
68 |
+
"vocab_size": 39985
|
69 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cae067c4236efbcbd83ea2dfdb8219b0dfdb483892575e455674cd82268651a5
|
3 |
+
size 467081572
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>"}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|