Update tokenizer_config.json
Browse files- tokenizer_config.json +3 -2
tokenizer_config.json
CHANGED
|
@@ -2050,7 +2050,7 @@
|
|
| 2050 |
}
|
| 2051 |
},
|
| 2052 |
"bos_token": "<|begin_of_text|>",
|
| 2053 |
-
"chat_template": "{{- bos_token }}\n{%-
|
| 2054 |
"clean_up_tokenization_spaces": true,
|
| 2055 |
"eos_token": "<|eot_id|>",
|
| 2056 |
"model_input_names": [
|
|
@@ -2058,6 +2058,7 @@
|
|
| 2058 |
"attention_mask"
|
| 2059 |
],
|
| 2060 |
"model_max_length": 131072,
|
| 2061 |
-
"pad_token": "<|
|
|
|
|
| 2062 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 2063 |
}
|
|
|
|
| 2050 |
}
|
| 2051 |
},
|
| 2052 |
"bos_token": "<|begin_of_text|>",
|
| 2053 |
+
"chat_template": "{{- bos_token }}\n{%- for message in messages %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n' }}\n {{- message['content'] + eos_token + '\n' }}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\n' }}\n{%- endif %}\n{%- if add_reasoning_prompt %}\n {{- '<|start_header_id|>reasoning<|end_header_id|>\n' }}\n{%- endif %}",
|
| 2054 |
"clean_up_tokenization_spaces": true,
|
| 2055 |
"eos_token": "<|eot_id|>",
|
| 2056 |
"model_input_names": [
|
|
|
|
| 2058 |
"attention_mask"
|
| 2059 |
],
|
| 2060 |
"model_max_length": 131072,
|
| 2061 |
+
"pad_token": "<|finetune_right_pad_id|>",
|
| 2062 |
+
"padding_side": "left",
|
| 2063 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 2064 |
}
|