hejunqing
commited on
Commit
•
a7eb0d6
1
Parent(s):
f518400
add model and config
Browse files- added_tokens.json +7 -0
- cases_t5_cmrc.png +0 -0
- config.json +31 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +12 -0
- tokenizer_config.json +11 -0
added_tokens.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[CTEND]": 32597,
|
3 |
+
"[CTSTART]": 32596,
|
4 |
+
"[KNEND]": 32600,
|
5 |
+
"[KNSTART]": 32599,
|
6 |
+
"[SEP]": 32598
|
7 |
+
}
|
cases_t5_cmrc.png
ADDED
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"MT5ForConditionalGeneration"
|
4 |
+
],
|
5 |
+
"d_ff": 2816,
|
6 |
+
"d_kv": 64,
|
7 |
+
"d_model": 1024,
|
8 |
+
"decoder_start_token_id": 0,
|
9 |
+
"dense_act_fn": "gelu_new",
|
10 |
+
"dropout_rate": 0.1,
|
11 |
+
"eos_token_id": 1,
|
12 |
+
"feed_forward_proj": "gated-gelu",
|
13 |
+
"initializer_factor": 1.0,
|
14 |
+
"is_encoder_decoder": true,
|
15 |
+
"is_gated_act": true,
|
16 |
+
"layer_norm_epsilon": 1e-06,
|
17 |
+
"model_type": "mt5",
|
18 |
+
"num_decoder_layers": 24,
|
19 |
+
"num_heads": 16,
|
20 |
+
"num_layers": 24,
|
21 |
+
"output_past": true,
|
22 |
+
"pad_token_id": 0,
|
23 |
+
"relative_attention_max_distance": 128,
|
24 |
+
"relative_attention_num_buckets": 32,
|
25 |
+
"tie_word_embeddings": false,
|
26 |
+
"tokenizer_class": "T5Tokenizer",
|
27 |
+
"torch_dtype": "float16",
|
28 |
+
"transformers_version": "4.21.1",
|
29 |
+
"use_cache": true,
|
30 |
+
"vocab_size": 32601
|
31 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92fe48b21c3b597398a026b3cd139aaae0425a8d0394b689be1c4346d7848089
|
3 |
+
size 1568317675
|
special_tokens_map.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"[CTSTART]",
|
4 |
+
"[CTEND]",
|
5 |
+
"[SEP]",
|
6 |
+
"[KNSTART]",
|
7 |
+
"[KNEND]"
|
8 |
+
],
|
9 |
+
"eos_token": "</s>",
|
10 |
+
"pad_token": "<pad>",
|
11 |
+
"unk_token": "<unk>"
|
12 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": null,
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"extra_ids": 0,
|
5 |
+
"name_or_path": "/cognitive_comp/hejunqing/projects/ChineseSquad/models/pretrained_epoch9/",
|
6 |
+
"pad_token": "<pad>",
|
7 |
+
"sp_model_kwargs": {},
|
8 |
+
"special_tokens_map_file": "/cognitive_comp/hejunqing/projects/ChineseSquad/models/pretrained_epoch9/special_tokens_map.json",
|
9 |
+
"tokenizer_class": "T5Tokenizer",
|
10 |
+
"unk_token": "<unk>"
|
11 |
+
}
|