Hugging Face's logo

lagodw
/
plotly_gpt_neo_1_3B

Text Generation
Transformers
PyTorch
gpt_neo
Inference Endpoints
Model card Files Community
lagodw commited on
Commit
4b3ae52
•
1 Parent(s): ecf7c07

full sample tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +1 -1
  2. special_tokens_map.json +1 -1
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +1 -1
added_tokens.json CHANGED
@@ -1 +1 @@
1
- {"<UNK>": 50257, "<PAD>": 50259, "<SEP>": 50258}
 
1
+ {"<UNK>": 50257, "<SEP>": 50258, "<PAD>": 50259}
special_tokens_map.json CHANGED
@@ -1 +1 @@
1
- {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": {"content": "<UNK>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": "<SEP>", "pad_token": "<PAD>"}
 
1
+ {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<UNK>", "sep_token": "<SEP>", "pad_token": "<PAD>"}
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1 +1 @@
1
- {"unk_token": {"content": "<UNK>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "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, "model_max_length": 2048, "special_tokens_map_file": null, "name_or_path": "EleutherAI/gpt-neo-1.3B", "pad_token": "<PAD>", "sep_token": "<SEP>", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}
 
1
+ {"unk_token": "<UNK>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "pad_token": "<PAD>", "sep_token": "<SEP>", "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2-medium", "tokenizer_class": "GPT2Tokenizer"}