casa commited on
Commit
97fcc3e
1 Parent(s): 15edd8c

initial configs and tokenizer

Browse files
Files changed (6) hide show
  1. config.json +31 -0
  2. merges.txt +0 -0
  3. special_tokens_map.json +6 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +34 -0
  6. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 1,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 2,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gpt2",
13
+ "n_ctx": 1024,
14
+ "n_embd": 1024,
15
+ "n_head": 16,
16
+ "n_layer": 24,
17
+ "n_positions": 1024,
18
+ "resid_pdrop": 0.1,
19
+ "summary_activation": null,
20
+ "summary_first_dropout": 0.1,
21
+ "summary_proj_to_labels": true,
22
+ "summary_type": "cls_index",
23
+ "summary_use_proj": true,
24
+ "task_specific_params": {
25
+ "text-generation": {
26
+ "do_sample": true,
27
+ "max_length": 50
28
+ }
29
+ },
30
+ "vocab_size": 51200
31
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "eos_token": {
13
+ "__type": "AddedToken",
14
+ "content": "</s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "errors": "replace",
21
+ "model_max_length": 1000000000000000019884624838656,
22
+ "name_or_path": "heegyu/ajoublue-gpt2-base",
23
+ "pad_token": null,
24
+ "special_tokens_map_file": null,
25
+ "tokenizer_class": "GPT2Tokenizer",
26
+ "unk_token": {
27
+ "__type": "AddedToken",
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff