patrickvonplaten commited on
Commit
d9874ea
1 Parent(s): 9b6c00a
Files changed (5) hide show
  1. config.json +2 -1
  2. merges.txt +0 -0
  3. special_tokens_map.json +1 -0
  4. tokenizer_config.json +1 -0
  5. vocab.json +0 -0
config.json CHANGED
@@ -22,5 +22,6 @@
22
  "transformers_version": "4.19.0.dev0",
23
  "use_cache": true,
24
  "vocab_size": 50272,
25
- "word_embed_proj_dim": 5120
 
26
  }
 
22
  "transformers_version": "4.19.0.dev0",
23
  "use_cache": true,
24
  "vocab_size": 50272,
25
+ "word_embed_proj_dim": 5120,
26
+ "prefix": "</s>"
27
  }
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": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"errors": "replace", "unk_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "add_bos_token": true, "special_tokens_map_file": null, "name_or_path": "patrickvonplaten/opt-30b", "tokenizer_class": "GPT2Tokenizer"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff