hhou435 commited on
Commit
2fb5b37
1 Parent(s): aaa75d9

First version of the gpt2-chinese-ancient model and tokenizer.

Browse files
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "embd_pdrop": 0.1,
8
+ "gradient_checkpointing": false,
9
+ "initializer_range": 0.02,
10
+ "layer_norm_epsilon": 1e-05,
11
+ "model_type": "gpt2",
12
+ "n_ctx": 1024,
13
+ "n_embd": 768,
14
+ "n_head": 12,
15
+ "n_inner": null,
16
+ "n_layer": 12,
17
+ "n_positions": 512,
18
+ "output_past": true,
19
+ "resid_pdrop": 0.1,
20
+ "task_specific_params": {
21
+ "text-generation": {
22
+ "do_sample": true,
23
+ "max_length": 400
24
+ }
25
+ },
26
+ "tokenizer_class": "BertTokenizer",
27
+ "vocab_size": 21128
28
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a335f4ea173e63bcacf1342ed63c7b588dfed5ed229f58432ba8014c91be548c
3
+ size 419348431
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c6097d4193a1566b845bebad27bfcedb8fe0477a18eedbb153f96052f7d2a4d
3
+ size 406876496
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff