Template update (#6)
Browse files- Template update (05e3c112c45091b75a3a50b6d6c2f0f8bb3c15da)
Co-authored-by: Pedro Cuenca <pcuenq@users.noreply.huggingface.co>
- tokenizer_config.json +2 -2
tokenizer_config.json
CHANGED
@@ -2058,14 +2058,14 @@
|
|
2058 |
}
|
2059 |
},
|
2060 |
"bos_token": "<|begin_of_text|>",
|
2061 |
-
"chat_template": "{% for message in messages %}{% if loop.index0 == 0 %}{{bos_token}}{% endif %}{{'<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n' }}{% for content in message['content'] %}{% if content['type'] == 'image' %}{{ '<|image|>' }}{% elif content['type'] == 'text' %}{{ content['text'] }}{% endif %}{% endfor %}{{ '<|eot_id|>' }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
2062 |
"clean_up_tokenization_spaces": true,
|
2063 |
"eos_token": "<|eot_id|>",
|
2064 |
"model_input_names": [
|
2065 |
"input_ids",
|
2066 |
"attention_mask"
|
2067 |
],
|
2068 |
-
"model_max_length":
|
2069 |
"pad_token": "<|finetune_right_pad_id|>",
|
2070 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
2071 |
}
|
|
|
2058 |
}
|
2059 |
},
|
2060 |
"bos_token": "<|begin_of_text|>",
|
2061 |
+
"chat_template": "{% for message in messages %}{% if loop.index0 == 0 %}{{ bos_token }}{% endif %}{{ '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n' }}{% if message['content'] is string %}{{ message['content'] }}{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' %}{{ '<|image|>' }}{% elif content['type'] == 'text' %}{{ content['text'] }}{% endif %}{% endfor %}{% endif %}{{ '<|eot_id|>' }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
2062 |
"clean_up_tokenization_spaces": true,
|
2063 |
"eos_token": "<|eot_id|>",
|
2064 |
"model_input_names": [
|
2065 |
"input_ids",
|
2066 |
"attention_mask"
|
2067 |
],
|
2068 |
+
"model_max_length": 131072,
|
2069 |
"pad_token": "<|finetune_right_pad_id|>",
|
2070 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
2071 |
}
|