GenueAI commited on
Commit
d92e9a6
·
verified ·
1 Parent(s): 2b58bff

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "classifier_dropout": 0.1,
52
+ "dtype": "float32",
53
+ "embed_dropout": 0,
54
+ "eos_token_id": 50256,
55
+ "gradient_checkpointing": false,
56
+ "hidden_size": 2560,
57
+ "initializer_range": 0.02,
58
+ "intermediate_size": null,
59
+ "layer_norm_epsilon": 1e-05,
60
+ "max_position_embeddings": 2048,
61
+ "model_type": "gpt_neo",
62
+ "num_heads": 20,
63
+ "num_layers": 32,
64
+ "pad_token_id": null,
65
+ "resid_dropout": 0,
66
+ "summary_activation": null,
67
+ "summary_first_dropout": 0.1,
68
+ "summary_proj_to_labels": true,
69
+ "summary_type": "cls_index",
70
+ "summary_use_proj": true,
71
+ "task_specific_params": {
72
+ "text-generation": {
73
+ "do_sample": true,
74
+ "max_length": 50,
75
+ "temperature": 0.9
76
+ }
77
+ },
78
+ "tie_word_embeddings": true,
79
+ "tokenizer_class": "GPT2Tokenizer",
80
+ "transformers_version": "5.0.0",
81
+ "use_cache": false,
82
+ "vocab_size": 50257,
83
+ "window_size": 256
84
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "5.0.0",
6
+ "use_cache": true
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db444743e73619cf4d9651fa8101203888dd09aa46a5b7fa0a63223881b44887
3
+ size 10605276536
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "eos_token": "<|endoftext|>",
6
+ "errors": "replace",
7
+ "is_local": false,
8
+ "model_max_length": 2048,
9
+ "pad_token": "<|endoftext|>",
10
+ "tokenizer_class": "GPT2Tokenizer",
11
+ "unk_token": "<|endoftext|>"
12
+ }