danielhanchen commited on
Commit
2e75c8b
·
verified ·
1 Parent(s): 1aa6b58

Upload processor

Browse files
special_tokens_map.json CHANGED
@@ -13,5 +13,11 @@
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
- "pad_token": "<|finetune_right_pad_id|>"
 
 
 
 
 
 
17
  }
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
  }
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:529d18ee0f18a8a446ae0b4310c6675823231b366a7ea3fddfc488cf7f2277d6
3
- size 17210149
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73c97d964e419f5dd8a8f0862987753c0bd60bfb1b82c3f4cc35cdba89250f9f
3
+ size 17210159
tokenizer_config.json CHANGED
@@ -2058,7 +2058,7 @@
2058
  "attention_mask"
2059
  ],
2060
  "model_max_length": 131072,
2061
- "pad_token": "<|finetune_right_pad_id|>",
2062
  "processor_class": "CsmProcessor",
2063
  "tokenizer_class": "PreTrainedTokenizer"
2064
  }
 
2058
  "attention_mask"
2059
  ],
2060
  "model_max_length": 131072,
2061
+ "pad_token": "<|end_of_text|>",
2062
  "processor_class": "CsmProcessor",
2063
  "tokenizer_class": "PreTrainedTokenizer"
2064
  }