Upload tokenizer
Browse files- tokenizer_config.json +8 -2
tokenizer_config.json
CHANGED
@@ -2050,16 +2050,22 @@
|
|
2050 |
}
|
2051 |
},
|
2052 |
"bos_token": "<|begin_of_text|>",
|
2053 |
-
"chat_template": "{
|
2054 |
"clean_up_tokenization_spaces": true,
|
2055 |
"eos_token": "<|eot_id|>",
|
2056 |
"extra_special_tokens": {},
|
|
|
2057 |
"model_input_names": [
|
2058 |
"input_ids",
|
2059 |
"attention_mask"
|
2060 |
],
|
2061 |
"model_max_length": 131072,
|
|
|
2062 |
"pad_token": "<|finetune_right_pad_id|>",
|
|
|
2063 |
"padding_side": "left",
|
2064 |
-
"
|
|
|
|
|
|
|
2065 |
}
|
|
|
2050 |
}
|
2051 |
},
|
2052 |
"bos_token": "<|begin_of_text|>",
|
2053 |
+
"chat_template": "{%- set ns = namespace(found=false) -%}{%- for message in messages -%}{%- if message['role'] == 'system' -%}{%- set ns.found = true -%}{%- endif -%}{%- endfor -%}{%- for message in messages %}{%- if message['role'] == 'system' -%}{{- '<|im_start|>system\n' + message['content'].rstrip() + '<|im_end|>\n' -}}{%- else -%}{%- if message['role'] == 'user' -%}{{-'<|im_start|>user\n' + message['content'].rstrip() + '<|im_end|>\n'-}}{%- else -%}{{-'<|im_start|>assistant\n' + message['content'] + '<|im_end|>\n' -}}{%- endif -%}{%- endif -%}{%- endfor -%}{%- if add_generation_prompt -%}{{-'<|im_start|>assistant\n'-}}{%- endif -%}",
|
2054 |
"clean_up_tokenization_spaces": true,
|
2055 |
"eos_token": "<|eot_id|>",
|
2056 |
"extra_special_tokens": {},
|
2057 |
+
"max_length": 1024,
|
2058 |
"model_input_names": [
|
2059 |
"input_ids",
|
2060 |
"attention_mask"
|
2061 |
],
|
2062 |
"model_max_length": 131072,
|
2063 |
+
"pad_to_multiple_of": null,
|
2064 |
"pad_token": "<|finetune_right_pad_id|>",
|
2065 |
+
"pad_token_type_id": 0,
|
2066 |
"padding_side": "left",
|
2067 |
+
"stride": 0,
|
2068 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
2069 |
+
"truncation_side": "right",
|
2070 |
+
"truncation_strategy": "longest_first"
|
2071 |
}
|