lg commited on
Commit
a827ee3
1 Parent(s): 17f3033
config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPTNeoForCausalLM"
5
+ ],
6
+ "attention_dropout": 0,
7
+ "attention_layers": [
8
+ "global",
9
+ "global",
10
+ "global",
11
+ "global",
12
+ "global",
13
+ "global",
14
+ "global",
15
+ "global",
16
+ "global",
17
+ "global",
18
+ "global",
19
+ "global",
20
+ "global",
21
+ "global",
22
+ "global",
23
+ "global",
24
+ "global",
25
+ "global",
26
+ "global",
27
+ "global",
28
+ "global",
29
+ "global",
30
+ "global",
31
+ "global",
32
+ "global",
33
+ "global",
34
+ "global",
35
+ "global",
36
+ "global",
37
+ "global",
38
+ "global",
39
+ "global"
40
+ ],
41
+ "attention_types": [
42
+ [
43
+ [
44
+ "global"
45
+ ],
46
+ 32
47
+ ]
48
+ ],
49
+ "bos_token_id": 50256,
50
+ "embed_dropout": 0,
51
+ "eos_token_id": 50256,
52
+ "gradient_checkpointing": false,
53
+ "hidden_size": 2560,
54
+ "initializer_range": 0.02,
55
+ "intermediate_size": null,
56
+ "layer_norm_epsilon": 1e-05,
57
+ "max_position_embeddings": 2048,
58
+ "model_type": "gpt_neo",
59
+ "num_heads": 32,
60
+ "num_layers": 32,
61
+ "resid_dropout": 0,
62
+ "summary_activation": null,
63
+ "summary_first_dropout": 0.1,
64
+ "summary_proj_to_labels": true,
65
+ "summary_type": "cls_index",
66
+ "summary_use_proj": true,
67
+ "transformers_version": "4.5.0.dev0",
68
+ "use_cache": true,
69
+ "vocab_size": 50257,
70
+ "window_size": 256
71
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2cd698c466f21620cc0046f3cb97b2460f2413b664301804b68f5f23900a703
3
+ size 10739613987
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"errors": "replace", "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 2048, "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