Hugging Face's logo

Copy6852
/
RoboSashaModel

Text Generation
Transformers
Safetensors
gpt_neo
Inference Endpoints
Model card Files Community
Copy6852 commited on
Commit
d89d410
•
1 Parent(s): 92c0303

Upload 9 files

Browse files
Files changed (9) hide show
  1. added_tokens.json +5 -0
  2. config.json +49 -0
  3. generation_config.json +7 -0
  4. merges.txt +0 -0
  5. model.safetensors +3 -0
  6. special_tokens_map.json +23 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +62 -0
  9. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 50257,
3
+ "<|startoftext|>": 50258,
4
+ "<|unknown|>": 50259
5
+ }
config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Norod78/hebrew-gpt_neo-tiny",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTNeoForCausalLM"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "attention_layers": [
9
+ "global",
10
+ "global",
11
+ "global",
12
+ "global",
13
+ "global",
14
+ "global"
15
+ ],
16
+ "attention_types": [
17
+ [
18
+ [
19
+ "global"
20
+ ],
21
+ 6
22
+ ]
23
+ ],
24
+ "bos_token_id": 50256,
25
+ "classifier_dropout": 0.1,
26
+ "embed_dropout": 0.1,
27
+ "eos_token_id": 50256,
28
+ "gradient_checkpointing": false,
29
+ "hidden_size": 768,
30
+ "initializer_range": 0.02,
31
+ "intermediate_size": null,
32
+ "layer_norm_epsilon": 1e-05,
33
+ "max_position_embeddings": 1024,
34
+ "model_type": "gpt_neo",
35
+ "num_heads": 12,
36
+ "num_layers": 6,
37
+ "pad_token_id": 2,
38
+ "resid_dropout": 0.1,
39
+ "summary_activation": null,
40
+ "summary_first_dropout": 0.1,
41
+ "summary_proj_to_labels": true,
42
+ "summary_type": "cls_index",
43
+ "summary_use_proj": true,
44
+ "torch_dtype": "float32",
45
+ "transformers_version": "4.37.2",
46
+ "use_cache": true,
47
+ "vocab_size": 50257,
48
+ "window_size": 256
49
+ }
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
+ "pad_token_id": 2,
6
+ "transformers_version": "4.37.2"
7
+ }
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:cb78beb144c57a3c23c6531764d335d209530f51b9cd8f75393579a1555806b9
3
+ size 327603624
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "2": {
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "3": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "50257": {
29
+ "content": "<|endoftext|>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": false
35
+ },
36
+ "50258": {
37
+ "content": "<|startoftext|>",
38
+ "lstrip": false,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": false
43
+ },
44
+ "50259": {
45
+ "content": "<|unknown|>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ }
52
+ },
53
+ "bos_token": "<s>",
54
+ "clean_up_tokenization_spaces": true,
55
+ "do_lower_case": false,
56
+ "eos_token": "</s>",
57
+ "full_tokenizer_file": null,
58
+ "max_len": 1024,
59
+ "model_max_length": 1024,
60
+ "tokenizer_class": "GPT2Tokenizer",
61
+ "unk_token": "<unk>"
62
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff