Hugging Face's logo

thisisHJLee
/
rm-model

Text Classification
Transformers
Safetensors
gpt_neo
Inference Endpoints
Model card Files Community
thisisHJLee commited on
Commit
4c256b9
•
1 Parent(s): 242a368

Upload 8 files

Browse files
Files changed (8) hide show
  1. added_tokens.json +4 -0
  2. config.json +75 -0
  3. merges.txt +0 -0
  4. model.safetensors +3 -0
  5. special_tokens_map.json +27 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +48 -0
  8. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|pad|>": 50258,
3
+ "<|startoftext|>": 50257
4
+ }
config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./output-10000-3epochs",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTNeoForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0,
8
+ "attention_layers": [
9
+ "global",
10
+ "local",
11
+ "global",
12
+ "local",
13
+ "global",
14
+ "local",
15
+ "global",
16
+ "local",
17
+ "global",
18
+ "local",
19
+ "global",
20
+ "local",
21
+ "global",
22
+ "local",
23
+ "global",
24
+ "local",
25
+ "global",
26
+ "local",
27
+ "global",
28
+ "local",
29
+ "global",
30
+ "local",
31
+ "global",
32
+ "local"
33
+ ],
34
+ "attention_types": [
35
+ [
36
+ [
37
+ "global",
38
+ "local"
39
+ ],
40
+ 12
41
+ ]
42
+ ],
43
+ "bos_token_id": 50256,
44
+ "classifier_dropout": 0.1,
45
+ "embed_dropout": 0,
46
+ "eos_token_id": 50256,
47
+ "gradient_checkpointing": false,
48
+ "hidden_size": 1024,
49
+ "id2label": {
50
+ "0": "LABEL_0"
51
+ },
52
+ "initializer_range": 0.02,
53
+ "intermediate_size": null,
54
+ "label2id": {
55
+ "LABEL_0": 0
56
+ },
57
+ "layer_norm_epsilon": 1e-05,
58
+ "max_position_embeddings": 2048,
59
+ "model_friendly_id": "PT_GPTNEO350_ATG",
60
+ "model_type": "gpt_neo",
61
+ "num_heads": 16,
62
+ "num_layers": 24,
63
+ "pad_token_id": 50256,
64
+ "resid_dropout": 0,
65
+ "summary_activation": null,
66
+ "summary_first_dropout": 0.1,
67
+ "summary_proj_to_labels": true,
68
+ "summary_type": "cls_index",
69
+ "summary_use_proj": true,
70
+ "torch_dtype": "float32",
71
+ "transformers_version": "4.38.2",
72
+ "use_cache": true,
73
+ "vocab_size": 50259,
74
+ "window_size": 256
75
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1dc34506908db8a9efbacbc26b483b067a4e8b219974e39a1e8220e2123ed16
3
+ size 1423238760
special_tokens_map.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>"
4
+ ],
5
+ "bos_token": {
6
+ "content": "<|startoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "eos_token": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "pad_token": "<|endoftext|>",
20
+ "unk_token": {
21
+ "content": "<|endoftext|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ }
27
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "50257": {
13
+ "content": "<|startoftext|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "50258": {
21
+ "content": "<|pad|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [
30
+ "<|endoftext|>"
31
+ ],
32
+ "bos_token": "<|startoftext|>",
33
+ "clean_up_tokenization_spaces": true,
34
+ "eos_token": "<|endoftext|>",
35
+ "errors": "replace",
36
+ "max_length": 291,
37
+ "model_max_length": 1000000000000000019884624838656,
38
+ "pad_to_multiple_of": null,
39
+ "pad_token": "<|endoftext|>",
40
+ "pad_token_type_id": 0,
41
+ "padding_side": "right",
42
+ "stride": 0,
43
+ "tokenizer_class": "GPT2Tokenizer",
44
+ "truncation_side": "right",
45
+ "truncation_strategy": "longest_first",
46
+ "unk_token": "<|endoftext|>",
47
+ "verbose": false
48
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff