Upload tokenizer_config.json with huggingface_hub
Browse files- tokenizer_config.json +3 -10
tokenizer_config.json
CHANGED
|
@@ -2047,18 +2047,10 @@
|
|
| 2047 |
"rstrip": false,
|
| 2048 |
"single_word": false,
|
| 2049 |
"special": true
|
| 2050 |
-
},
|
| 2051 |
-
"128256": {
|
| 2052 |
-
"content": "[PAD]",
|
| 2053 |
-
"lstrip": false,
|
| 2054 |
-
"normalized": false,
|
| 2055 |
-
"rstrip": false,
|
| 2056 |
-
"single_word": false,
|
| 2057 |
-
"special": true
|
| 2058 |
}
|
| 2059 |
},
|
| 2060 |
"bos_token": "<|begin_of_text|>",
|
| 2061 |
-
"chat_template": "{{- bos_token }}\n{
|
| 2062 |
"clean_up_tokenization_spaces": true,
|
| 2063 |
"eos_token": "<|eot_id|>",
|
| 2064 |
"extra_special_tokens": {},
|
|
@@ -2067,6 +2059,7 @@
|
|
| 2067 |
"attention_mask"
|
| 2068 |
],
|
| 2069 |
"model_max_length": 131072,
|
| 2070 |
-
"pad_token": "
|
|
|
|
| 2071 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 2072 |
}
|
|
|
|
| 2047 |
"rstrip": false,
|
| 2048 |
"single_word": false,
|
| 2049 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2050 |
}
|
| 2051 |
},
|
| 2052 |
"bos_token": "<|begin_of_text|>",
|
| 2053 |
+
"chat_template": "{{- bos_token }}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{{messages[0]['content']|trim}}{{- \"<|start_header_id|>user<|end_header_id|>\\n\\n\" -}}\n{{messages[1]['content']|trim}}<|eot_id|>{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- if messages[2] is defined %}\n{{messages[2]['content']|trim}}<|eot_id|>{%- endif %}{%- endif %}\n",
|
| 2054 |
"clean_up_tokenization_spaces": true,
|
| 2055 |
"eos_token": "<|eot_id|>",
|
| 2056 |
"extra_special_tokens": {},
|
|
|
|
| 2059 |
"attention_mask"
|
| 2060 |
],
|
| 2061 |
"model_max_length": 131072,
|
| 2062 |
+
"pad_token": "<|finetune_right_pad_id|>",
|
| 2063 |
+
"padding_side": "left",
|
| 2064 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 2065 |
}
|