Rachel Bawden
commited on
Commit
•
744a36a
1
Parent(s):
61afd96
add base model just converted
Browse files- config.json +38 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab-src.json +0 -0
- vocab-tgt.json +0 -0
config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"AutoModelForSeq2SeqLM"
|
4 |
+
],
|
5 |
+
"model_type": "fsmt",
|
6 |
+
"activation_dropout": 0.0,
|
7 |
+
"activation_function": "relu",
|
8 |
+
"attention_dropout": 0.0,
|
9 |
+
"d_model": 512,
|
10 |
+
"dropout": 0.1,
|
11 |
+
"init_std": 0.02,
|
12 |
+
"max_position_embeddings": 1024,
|
13 |
+
"num_hidden_layers": 6,
|
14 |
+
"src_vocab_size": 7968,
|
15 |
+
"tgt_vocab_size": 7968,
|
16 |
+
"langs": [
|
17 |
+
"sommaire",
|
18 |
+
"titrage"
|
19 |
+
],
|
20 |
+
"encoder_attention_heads": 8,
|
21 |
+
"encoder_ffn_dim": 2048,
|
22 |
+
"encoder_layerdrop": 0,
|
23 |
+
"encoder_layers": 6,
|
24 |
+
"decoder_attention_heads": 8,
|
25 |
+
"decoder_ffn_dim": 2048,
|
26 |
+
"decoder_layerdrop": 0,
|
27 |
+
"decoder_layers": 6,
|
28 |
+
"bos_token_id": 0,
|
29 |
+
"pad_token_id": 1,
|
30 |
+
"eos_token_id": 2,
|
31 |
+
"unk_token_id": 3,
|
32 |
+
"is_encoder_decoder": true,
|
33 |
+
"scale_embedding": true,
|
34 |
+
"tie_word_embeddings": true,
|
35 |
+
"num_beams": 5,
|
36 |
+
"early_stopping": false,
|
37 |
+
"length_penalty": 1.0
|
38 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2bfbd15078882bae5054cd2bdbd8528b451800b319ab7e3a1209e5c0a74bb2a4
|
3 |
+
size 192952903
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "<unk>", "eos_token": "</s>", "bos_token": "<s>", "pad_token": "<pad>", "tokenizer_class": "PreTrainedTokenizerFast"}
|
vocab-src.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
vocab-tgt.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|