Check-in of best timex model for thyme colon data.
Browse files- added_tokens.json +1 -0
- config.json +29 -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
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"</e>": 50266, "<cr>": 50271, "</a1>": 50268, "<a2>": 50269, "</a2>": 50270, "<e>": 50265, "<neg>": 50272, "<a1>": 50267}
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"CnlpRobertaForClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"finetuning_task": [
|
10 |
+
"timex"
|
11 |
+
],
|
12 |
+
"gradient_checkpointing": false,
|
13 |
+
"hidden_act": "gelu",
|
14 |
+
"hidden_dropout_prob": 0.1,
|
15 |
+
"hidden_size": 768,
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 3072,
|
18 |
+
"layer_norm_eps": 1e-05,
|
19 |
+
"max_position_embeddings": 514,
|
20 |
+
"model_type": "roberta",
|
21 |
+
"num_attention_heads": 12,
|
22 |
+
"num_hidden_layers": 12,
|
23 |
+
"pad_token_id": 1,
|
24 |
+
"position_embedding_type": "absolute",
|
25 |
+
"transformers_version": "4.4.0.dev0",
|
26 |
+
"type_vocab_size": 1,
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 50273
|
29 |
+
}
|
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 sha256:2b6d9e12a6ca50ee533a1636060513aeedfd0c5ebdb729da57f27cbb6ceb1f45
|
3 |
+
size 501078293
|
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": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}, "additional_special_tokens": ["<e>", "</e>", "<a1>", "</a1>", "<a2>", "</a2>", "<cr>", "<neg>"]}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": true, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "additional_special_tokens": ["<e>", "</e>", "<a1>", "</a1>", "<a2>", "</a2>", "<cr>", "<neg>"], "model_max_length": 512, "name_or_path": "roberta-base"}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|