Doron Adler commited on
Commit
420342d
1 Parent(s): 40ab72c

Checkpoint 390500

Browse files
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPTNeoForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "attention_layers": [
8
+ "global",
9
+ "global",
10
+ "global",
11
+ "global",
12
+ "global",
13
+ "global"
14
+ ],
15
+ "attention_types": [
16
+ [
17
+ [
18
+ "global"
19
+ ],
20
+ 6
21
+ ]
22
+ ],
23
+ "bos_token_id": 50256,
24
+ "embed_dropout": 0.1,
25
+ "eos_token_id": 50256,
26
+ "gradient_checkpointing": false,
27
+ "hidden_size": 768,
28
+ "initializer_range": 0.02,
29
+ "intermediate_size": null,
30
+ "layer_norm_epsilon": 1e-05,
31
+ "max_position_embeddings": 1024,
32
+ "model_type": "gpt_neo",
33
+ "num_heads": 12,
34
+ "num_layers": 6,
35
+ "resid_dropout": 0.1,
36
+ "summary_activation": null,
37
+ "summary_first_dropout": 0.1,
38
+ "summary_proj_to_labels": true,
39
+ "summary_type": "cls_index",
40
+ "summary_use_proj": true,
41
+ "transformers_version": "4.5.1",
42
+ "use_cache": true,
43
+ "vocab_size": 50257,
44
+ "window_size": 256
45
+ }
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 sha256:6dc6b9177a99ec20e2a8d9b629ba10496c27c3376a85ac11f23d9b25e651c7da
3
+ size 333916933
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<|startoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|unknown|>"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": false, "max_len": 1024, "bos_token": "<|startoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "special_tokens_map_file": "special_tokens_map.json", "full_tokenizer_file": null}
vocab.json ADDED
The diff for this file is too large to render. See raw diff