DavidLanz commited on
Commit
e1979b7
·
1 Parent(s): 38cea23

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. config.json +1 -1
  2. pytorch_model.bin +1 -1
  3. tokenizer.json +1 -1
  4. tokenizer_config.json +4 -0
  5. vocab.json +0 -0
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "gpt2",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPT2LMHeadModel"
 
1
  {
2
+ "_name_or_path": "DavidLanz/tcp2023",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPT2LMHeadModel"
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa9b3c82bb6bf9f0b65d7230af2848eb99e72252fe2ea25f75ec15f502fe3661
3
  size 497807706
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6988c521d4b1a468a7a41a3e9dd4b9f113a8994dd0521f6f693703448521163d
3
  size 497807706
tokenizer.json CHANGED
@@ -14,7 +14,7 @@
14
  "single_word": false,
15
  "lstrip": false,
16
  "rstrip": false,
17
- "normalized": false,
18
  "special": true
19
  }
20
  ],
 
14
  "single_word": false,
15
  "lstrip": false,
16
  "rstrip": false,
17
+ "normalized": true,
18
  "special": true
19
  }
20
  ],
tokenizer_config.json CHANGED
@@ -15,8 +15,12 @@
15
  "clean_up_tokenization_spaces": true,
16
  "eos_token": "<|endoftext|>",
17
  "errors": "replace",
 
18
  "model_max_length": 1024,
19
  "pad_token": null,
 
20
  "tokenizer_class": "GPT2Tokenizer",
 
 
21
  "unk_token": "<|endoftext|>"
22
  }
 
15
  "clean_up_tokenization_spaces": true,
16
  "eos_token": "<|endoftext|>",
17
  "errors": "replace",
18
+ "max_length": 200,
19
  "model_max_length": 1024,
20
  "pad_token": null,
21
+ "stride": 0,
22
  "tokenizer_class": "GPT2Tokenizer",
23
+ "truncation_side": "right",
24
+ "truncation_strategy": "longest_first",
25
  "unk_token": "<|endoftext|>"
26
  }
vocab.json CHANGED
The diff for this file is too large to render. See raw diff