Upload processor
Browse files- chat_template.json +3 -0
- preprocessor_config.json +0 -0
- tokenizer_config.json +4 -0
chat_template.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}"
|
3 |
+
}
|
preprocessor_config.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -119,8 +119,12 @@
|
|
119 |
"clean_up_tokenization_spaces": false,
|
120 |
"eos_token": "<|endoftext|>",
|
121 |
"extra_special_tokens": {},
|
|
|
122 |
"model_max_length": 131072,
|
|
|
123 |
"pad_token": "<|endoftext|>",
|
|
|
|
|
124 |
"processor_class": "Phi4MMProcessor",
|
125 |
"tokenizer_class": "GPT2Tokenizer",
|
126 |
"unk_token": "<|endoftext|>"
|
|
|
119 |
"clean_up_tokenization_spaces": false,
|
120 |
"eos_token": "<|endoftext|>",
|
121 |
"extra_special_tokens": {},
|
122 |
+
"max_length": null,
|
123 |
"model_max_length": 131072,
|
124 |
+
"pad_to_multiple_of": null,
|
125 |
"pad_token": "<|endoftext|>",
|
126 |
+
"pad_token_type_id": 0,
|
127 |
+
"padding_side": "right",
|
128 |
"processor_class": "Phi4MMProcessor",
|
129 |
"tokenizer_class": "GPT2Tokenizer",
|
130 |
"unk_token": "<|endoftext|>"
|