Push tokenizer again (
#2)
 
		023abf6
		verified
		 
			
			
				
					
						
						| 
							 | 
						{
 | 
					
					
						
						| 
							 | 
						  "bos_token": {
 | 
					
					
						
						| 
							 | 
						    "content": "<s>",
 | 
					
					
						
						| 
							 | 
						    "lstrip": false,
 | 
					
					
						
						| 
							 | 
						    "normalized": true,
 | 
					
					
						
						| 
							 | 
						    "rstrip": false,
 | 
					
					
						
						| 
							 | 
						    "single_word": false
 | 
					
					
						
						| 
							 | 
						  },
 | 
					
					
						
						| 
							 | 
						  "cls_token": {
 | 
					
					
						
						| 
							 | 
						    "content": "<s>",
 | 
					
					
						
						| 
							 | 
						    "lstrip": false,
 | 
					
					
						
						| 
							 | 
						    "normalized": true,
 | 
					
					
						
						| 
							 | 
						    "rstrip": false,
 | 
					
					
						
						| 
							 | 
						    "single_word": false
 | 
					
					
						
						| 
							 | 
						  },
 | 
					
					
						
						| 
							 | 
						  "eos_token": {
 | 
					
					
						
						| 
							 | 
						    "content": "</s>",
 | 
					
					
						
						| 
							 | 
						    "lstrip": false,
 | 
					
					
						
						| 
							 | 
						    "normalized": true,
 | 
					
					
						
						| 
							 | 
						    "rstrip": false,
 | 
					
					
						
						| 
							 | 
						    "single_word": false
 | 
					
					
						
						| 
							 | 
						  },
 | 
					
					
						
						| 
							 | 
						  "mask_token": {
 | 
					
					
						
						| 
							 | 
						    "content": "<mask>",
 | 
					
					
						
						| 
							 | 
						    "lstrip": true,
 | 
					
					
						
						| 
							 | 
						    "normalized": true,
 | 
					
					
						
						| 
							 | 
						    "rstrip": false,
 | 
					
					
						
						| 
							 | 
						    "single_word": false
 | 
					
					
						
						| 
							 | 
						  },
 | 
					
					
						
						| 
							 | 
						  "pad_token": {
 | 
					
					
						
						| 
							 | 
						    "content": "<pad>",
 | 
					
					
						
						| 
							 | 
						    "lstrip": false,
 | 
					
					
						
						| 
							 | 
						    "normalized": true,
 | 
					
					
						
						| 
							 | 
						    "rstrip": false,
 | 
					
					
						
						| 
							 | 
						    "single_word": false
 | 
					
					
						
						| 
							 | 
						  },
 | 
					
					
						
						| 
							 | 
						  "sep_token": {
 | 
					
					
						
						| 
							 | 
						    "content": "</s>",
 | 
					
					
						
						| 
							 | 
						    "lstrip": false,
 | 
					
					
						
						| 
							 | 
						    "normalized": true,
 | 
					
					
						
						| 
							 | 
						    "rstrip": false,
 | 
					
					
						
						| 
							 | 
						    "single_word": false
 | 
					
					
						
						| 
							 | 
						  },
 | 
					
					
						
						| 
							 | 
						  "unk_token": {
 | 
					
					
						
						| 
							 | 
						    "content": "<unk>",
 | 
					
					
						
						| 
							 | 
						    "lstrip": false,
 | 
					
					
						
						| 
							 | 
						    "normalized": true,
 | 
					
					
						
						| 
							 | 
						    "rstrip": false,
 | 
					
					
						
						| 
							 | 
						    "single_word": false
 | 
					
					
						
						| 
							 | 
						  }
 | 
					
					
						
						| 
							 | 
						}
 | 
					
					
						
						| 
							 | 
						
 |