Doron Adler commited on
Commit
7cd1648
1 Parent(s): 9c3492d

norod78/hebrew_poetry-gpt_neo-small

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
1
+ {"<|startoftext|>": 50258, "<|endoftext|>": 50257, "<|unknown|>": 50259}
config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/content/trained_model",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTNeoForCausalLM"
6
+ ],
7
+ "attention_dropout": 0,
8
+ "attention_layers": [
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
+ ],
22
+ "attention_types": [
23
+ [
24
+ [
25
+ "global"
26
+ ],
27
+ 12
28
+ ]
29
+ ],
30
+ "bos_token_id": 50256,
31
+ "embed_dropout": 0,
32
+ "eos_token_id": 50256,
33
+ "gradient_checkpointing": false,
34
+ "hidden_size": 768,
35
+ "initializer_range": 0.02,
36
+ "intermediate_size": null,
37
+ "layer_norm_epsilon": 1e-05,
38
+ "line_by_line": false,
39
+ "max_position_embeddings": 2048,
40
+ "model_type": "gpt_neo",
41
+ "num_heads": 12,
42
+ "num_layers": 12,
43
+ "resid_dropout": 0,
44
+ "summary_activation": null,
45
+ "summary_first_dropout": 0.1,
46
+ "summary_proj_to_labels": true,
47
+ "summary_type": "cls_index",
48
+ "summary_use_proj": true,
49
+ "transformers_version": "4.6.0",
50
+ "use_cache": true,
51
+ "vocab_size": 50257,
52
+ "window_size": 256
53
+ }
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:a2d57f4dfd710726421fe9fd5d0f2155aaca39d8aec5764f8f4cad33bd84ae8a
3
+ size 551187431
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": "<|startoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|unknown|>"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|startoftext|>", "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, "do_lower_case": false, "max_len": 1024, "special_tokens_map_file": "special_tokens_map.json", "full_tokenizer_file": null, "name_or_path": "/content/trained_model", "errors": "replace"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff