hf-transformers-bot
commited on
Commit
•
b3274b8
1
Parent(s):
aad63d2
Upload tiny models for FlaubertModel
Browse files- config.json +47 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +20 -0
- tf_model.h5 +3 -0
- tokenizer_config.json +27 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "tiny_models/flaubert/FlaubertModel",
|
3 |
+
"architectures": [
|
4 |
+
"FlaubertModel"
|
5 |
+
],
|
6 |
+
"asm": false,
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"bos_index": 0,
|
9 |
+
"bos_token_id": 0,
|
10 |
+
"causal": false,
|
11 |
+
"dropout": 0.1,
|
12 |
+
"emb_dim": 32,
|
13 |
+
"embed_init_std": 0.02209708691207961,
|
14 |
+
"end_n_top": 5,
|
15 |
+
"eos_index": 1,
|
16 |
+
"gelu_activation": true,
|
17 |
+
"init_std": 0.02,
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"is_encoder": true,
|
20 |
+
"lang_id": 0,
|
21 |
+
"layer_norm_eps": 1e-12,
|
22 |
+
"layerdrop": 0.0,
|
23 |
+
"mask_index": 5,
|
24 |
+
"mask_token_id": 5,
|
25 |
+
"max_position_embeddings": 512,
|
26 |
+
"model_type": "flaubert",
|
27 |
+
"n_heads": 4,
|
28 |
+
"n_langs": 2,
|
29 |
+
"n_layers": 5,
|
30 |
+
"n_special": 0,
|
31 |
+
"pad_index": 2,
|
32 |
+
"pad_token_id": 2,
|
33 |
+
"pre_norm": false,
|
34 |
+
"sinusoidal_embeddings": false,
|
35 |
+
"start_n_top": 5,
|
36 |
+
"summary_activation": null,
|
37 |
+
"summary_first_dropout": 0.1,
|
38 |
+
"summary_proj_to_labels": true,
|
39 |
+
"summary_type": "last",
|
40 |
+
"summary_use_proj": true,
|
41 |
+
"torch_dtype": "float32",
|
42 |
+
"transformers_version": "4.28.0.dev0",
|
43 |
+
"unk_index": 3,
|
44 |
+
"use_lang_emb": true,
|
45 |
+
"use_proj": null,
|
46 |
+
"vocab_size": 67542
|
47 |
+
}
|
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:c5f973a31031923145ea7bb010448a8381cba8f0a844406df2a3a4ed7df8574e
|
3 |
+
size 8990704
|
special_tokens_map.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<special0>",
|
4 |
+
"<special1>",
|
5 |
+
"<special2>",
|
6 |
+
"<special3>",
|
7 |
+
"<special4>",
|
8 |
+
"<special5>",
|
9 |
+
"<special6>",
|
10 |
+
"<special7>",
|
11 |
+
"<special8>",
|
12 |
+
"<special9>"
|
13 |
+
],
|
14 |
+
"bos_token": "<s>",
|
15 |
+
"cls_token": "</s>",
|
16 |
+
"mask_token": "<special1>",
|
17 |
+
"pad_token": "<pad>",
|
18 |
+
"sep_token": "</s>",
|
19 |
+
"unk_token": "<unk>"
|
20 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:21dc5f964f1a11f5b4c302c800374cb3fb3cda0db19503e314b4435f2ba26049
|
3 |
+
size 9062864
|
tokenizer_config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<special0>",
|
4 |
+
"<special1>",
|
5 |
+
"<special2>",
|
6 |
+
"<special3>",
|
7 |
+
"<special4>",
|
8 |
+
"<special5>",
|
9 |
+
"<special6>",
|
10 |
+
"<special7>",
|
11 |
+
"<special8>",
|
12 |
+
"<special9>"
|
13 |
+
],
|
14 |
+
"bos_token": "<s>",
|
15 |
+
"clean_up_tokenization_spaces": true,
|
16 |
+
"cls_token": "</s>",
|
17 |
+
"do_lower_case": true,
|
18 |
+
"id2lang": null,
|
19 |
+
"lang2id": null,
|
20 |
+
"mask_token": "<special1>",
|
21 |
+
"model_max_length": 512,
|
22 |
+
"pad_token": "<pad>",
|
23 |
+
"sep_token": "</s>",
|
24 |
+
"special_tokens_map_file": null,
|
25 |
+
"tokenizer_class": "FlaubertTokenizer",
|
26 |
+
"unk_token": "<unk>"
|
27 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|