Add v2 files
Browse files- config.json +6 -4
- flax_model.msgpack +2 -2
- merges.txt +0 -0
- pytorch_model.bin +2 -2
- special_tokens_map.json +1 -1
- tokenizer.json +0 -0
- tokenizer_config.json +1 -1
- vocab.json +0 -0
config.json
CHANGED
@@ -1,13 +1,15 @@
|
|
1 |
{
|
|
|
2 |
"architectures": [
|
3 |
"RobertaForMaskedLM"
|
4 |
],
|
5 |
-
"attention_probs_dropout_prob": 0.
|
6 |
"bos_token_id": 0,
|
|
|
7 |
"eos_token_id": 2,
|
8 |
"gradient_checkpointing": false,
|
9 |
"hidden_act": "gelu",
|
10 |
-
"hidden_dropout_prob": 0.
|
11 |
"hidden_size": 768,
|
12 |
"initializer_range": 0.02,
|
13 |
"intermediate_size": 3072,
|
@@ -18,8 +20,8 @@
|
|
18 |
"num_hidden_layers": 12,
|
19 |
"pad_token_id": 1,
|
20 |
"position_embedding_type": "absolute",
|
21 |
-
"transformers_version": "4.
|
22 |
"type_vocab_size": 1,
|
23 |
"use_cache": true,
|
24 |
-
"vocab_size":
|
25 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "./",
|
3 |
"architectures": [
|
4 |
"RobertaForMaskedLM"
|
5 |
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
"eos_token_id": 2,
|
10 |
"gradient_checkpointing": false,
|
11 |
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.0,
|
13 |
"hidden_size": 768,
|
14 |
"initializer_range": 0.02,
|
15 |
"intermediate_size": 3072,
|
|
|
20 |
"num_hidden_layers": 12,
|
21 |
"pad_token_id": 1,
|
22 |
"position_embedding_type": "absolute",
|
23 |
+
"transformers_version": "4.17.0.dev0",
|
24 |
"type_vocab_size": 1,
|
25 |
"use_cache": true,
|
26 |
+
"vocab_size": 50262
|
27 |
}
|
flax_model.msgpack
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd0b03d96beadabf4221aba83cde8b6239dcbb20cfdcb4062506465f50deeed3
|
3 |
+
size 498787755
|
merges.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84f20e57e59afca5201e92ded653780bfbae23de5d29578f30e09fed28ea0461
|
3 |
+
size 498864299
|
special_tokens_map.json
CHANGED
@@ -1 +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":
|
|
|
1 |
+
{"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"
|
|
|
1 |
+
{"errors": "replace", "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "trim_offsets": true, "max_len": 512, "special_tokens_map_file": null, "name_or_path": "./", "tokenizer_class": "RobertaTokenizer"}
|
vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|