shibing624
commited on
Commit
•
1d10dfd
1
Parent(s):
16d3497
Upload 5 files
Browse files- config.json +21 -7
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -0
- vocab.txt +1 -1
config.json
CHANGED
@@ -1,26 +1,40 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
2 |
"attn_pdrop": 0.1,
|
|
|
3 |
"embd_pdrop": 0.1,
|
4 |
-
"
|
|
|
|
|
|
|
5 |
"initializer_range": 0.02,
|
|
|
|
|
|
|
6 |
"layer_norm_epsilon": 1e-05,
|
|
|
7 |
"n_ctx": 300,
|
8 |
"n_embd": 768,
|
9 |
"n_head": 12,
|
|
|
10 |
"n_layer": 10,
|
11 |
"n_positions": 300,
|
12 |
-
"num_labels": 1,
|
13 |
-
"output_attentions": false,
|
14 |
-
"output_hidden_states": false,
|
15 |
"output_past": true,
|
16 |
-
"
|
17 |
"resid_pdrop": 0.1,
|
|
|
|
|
18 |
"summary_activation": null,
|
19 |
"summary_first_dropout": 0.1,
|
20 |
"summary_proj_to_labels": true,
|
21 |
"summary_type": "cls_index",
|
22 |
"summary_use_proj": true,
|
23 |
-
"
|
24 |
-
"
|
|
|
25 |
"vocab_size": 13317
|
26 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "shibing624/gpt2-dialogbot-base-chinese",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0"
|
13 |
+
},
|
14 |
"initializer_range": 0.02,
|
15 |
+
"label2id": {
|
16 |
+
"LABEL_0": 0
|
17 |
+
},
|
18 |
"layer_norm_epsilon": 1e-05,
|
19 |
+
"model_type": "gpt2",
|
20 |
"n_ctx": 300,
|
21 |
"n_embd": 768,
|
22 |
"n_head": 12,
|
23 |
+
"n_inner": null,
|
24 |
"n_layer": 10,
|
25 |
"n_positions": 300,
|
|
|
|
|
|
|
26 |
"output_past": true,
|
27 |
+
"reorder_and_upcast_attn": false,
|
28 |
"resid_pdrop": 0.1,
|
29 |
+
"scale_attn_by_inverse_layer_idx": false,
|
30 |
+
"scale_attn_weights": true,
|
31 |
"summary_activation": null,
|
32 |
"summary_first_dropout": 0.1,
|
33 |
"summary_proj_to_labels": true,
|
34 |
"summary_type": "cls_index",
|
35 |
"summary_use_proj": true,
|
36 |
+
"torch_dtype": "float32",
|
37 |
+
"transformers_version": "4.20.1",
|
38 |
+
"use_cache": true,
|
39 |
"vocab_size": 13317
|
40 |
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_basic_tokenize": true,
|
4 |
+
"do_lower_case": true,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"name_or_path": "shibing624/gpt2-dialogbot-base-chinese",
|
7 |
+
"never_split": null,
|
8 |
+
"pad_token": "[PAD]",
|
9 |
+
"sep_token": "[SEP]",
|
10 |
+
"special_tokens_map_file": null,
|
11 |
+
"strip_accents": null,
|
12 |
+
"tokenize_chinese_chars": true,
|
13 |
+
"tokenizer_class": "BertTokenizer",
|
14 |
+
"unk_token": "[UNK]"
|
15 |
+
}
|
vocab.txt
CHANGED
@@ -13314,4 +13314,4 @@ publishing
|
|
13314 |
e88
|
13315 |
970
|
13316 |
##dog
|
13317 |
-
fishbase
|
|
|
13314 |
e88
|
13315 |
970
|
13316 |
##dog
|
13317 |
+
fishbase
|