ali101 commited on
Commit
a409ba1
1 Parent(s): ebd1f98

Training in progress, step 500

Browse files
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5058fe795e38a103d07a53b2503d072da79546b6543debf0958f7c5f811a27b
3
  size 327657928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65225b1a9a8d2c6e0c76792f210c0f4770d4e91a5bb9bf2ad60f41ce31c60190
3
  size 327657928
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": true,
15
+ "eos_token": "<|endoftext|>",
16
+ "model_max_length": 1024,
17
+ "pad_token": "<|endoftext|>",
18
+ "tokenizer_class": "GPT2Tokenizer",
19
+ "unk_token": "<|endoftext|>"
20
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8f2504e37e6d2ffd4774866b3d1b772d4e18f416e669d058cc7a129d93bdfba
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25294887c1167290dfe192ec0e994f5a32bf8b785e1a508e1d6df08efd6587ab
3
  size 5112
vocab.json ADDED
The diff for this file is too large to render. See raw diff