Ssarion commited on
Commit
b874c63
1 Parent(s): 6c9b4b2

Training in progress, step 500

Browse files
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d0f4e1a1b9967966e29fa95ce2f005605a381eee097c597302ace9314a12138f
3
  size 510398013
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:079a708b9375ed602a1a9900ffefe58e859791068aa12c42dd5bb0e57fb69f00
3
  size 510398013
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 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "eos_token": "<|endoftext|>",
6
+ "model_max_length": 1024,
7
+ "tokenizer_class": "GPT2Tokenizer",
8
+ "unk_token": "<|endoftext|>"
9
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:740ebe2dd19182135363e352ab54d59cfd05e2d6af2ecf7b62f41832daa8e9d1
3
  size 3579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d425182708e8f19e894ee53fd8515ee1013ae1d7f19936ad1934beacccd04196
3
  size 3579
vocab.json ADDED
The diff for this file is too large to render. See raw diff