brimeggi commited on
Commit
5f6267f
1 Parent(s): 8e9dbc7

add tokenizer

Browse files
README.md ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - conversational
4
+ ---
5
+ # RickBot built for [Chai](https://chai.ml/)
6
+ Make your own [here](https://colab.research.google.com/drive/1o5LxBspm-C28HQvXN-PRQavapDbm5WjG?usp=sharing)
merges.txt ADDED
The diff for this file is too large to render. See raw diff
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": {"content": "<|endoftext|>", "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": 1024, "special_tokens_map_file": null, "name_or_path": "microsoft/DialoGPT-small", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff