nostalgebraist commited on
Commit
84bb410
1 Parent(s): 3253350

Initial commit

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<|padding|>": 50257}
config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPTNeoForCausalLM"
5
+ ],
6
+ "attention_dropout": 0,
7
+ "attention_layers": [
8
+ "global",
9
+ "local",
10
+ "global",
11
+ "local",
12
+ "global",
13
+ "local",
14
+ "global",
15
+ "local",
16
+ "global",
17
+ "local",
18
+ "global",
19
+ "local",
20
+ "global",
21
+ "local",
22
+ "global",
23
+ "local",
24
+ "global",
25
+ "local",
26
+ "global",
27
+ "local",
28
+ "global",
29
+ "local",
30
+ "global",
31
+ "local",
32
+ "global",
33
+ "local",
34
+ "global",
35
+ "local",
36
+ "global",
37
+ "local",
38
+ "global",
39
+ "local"
40
+ ],
41
+ "attention_types": [
42
+ [
43
+ [
44
+ "global",
45
+ "local"
46
+ ],
47
+ 16
48
+ ]
49
+ ],
50
+ "bos_token_id": 50256,
51
+ "embed_dropout": 0,
52
+ "eos_token_id": 50256,
53
+ "gradient_checkpointing": false,
54
+ "hidden_size": 2560,
55
+ "initializer_range": 0.02,
56
+ "intermediate_size": null,
57
+ "layer_norm_epsilon": 1e-05,
58
+ "max_position_embeddings": 2048,
59
+ "model_type": "gpt_neo",
60
+ "num_heads": 20,
61
+ "num_layers": 32,
62
+ "resid_dropout": 0,
63
+ "summary_activation": null,
64
+ "summary_first_dropout": 0.1,
65
+ "summary_proj_to_labels": true,
66
+ "summary_type": "cls_index",
67
+ "summary_use_proj": true,
68
+ "transformers_version": "4.5.1",
69
+ "use_cache": true,
70
+ "vocab_size": 50257,
71
+ "window_size": 256
72
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "pad_token": "<|padding|>"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "max_model_len": 2048, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff