Add default chat template to tokenizer_config.json
Browse files[Automated] This PR adds the default chat template to the tokenizer config, allowing the model to be used with the new conversational widget (see [PR](https://github.com/huggingface/huggingface.js/pull/457)).
If the default is not appropriate for your model, please set `tokenizer.chat_template` to an appropriate template. See https://huggingface.co/docs/transformers/main/chat_templating for more information.
- tokenizer_config.json +33 -1
tokenizer_config.json
CHANGED
|
@@ -1 +1,33 @@
|
|
| 1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"unk_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"single_word": false,
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"__type": "AddedToken"
|
| 9 |
+
},
|
| 10 |
+
"bos_token": {
|
| 11 |
+
"content": "<|endoftext|>",
|
| 12 |
+
"single_word": false,
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"__type": "AddedToken"
|
| 17 |
+
},
|
| 18 |
+
"eos_token": {
|
| 19 |
+
"content": "<|endoftext|>",
|
| 20 |
+
"single_word": false,
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"rstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"__type": "AddedToken"
|
| 25 |
+
},
|
| 26 |
+
"add_prefix_space": false,
|
| 27 |
+
"model_max_length": 1024,
|
| 28 |
+
"special_tokens_map_file": null,
|
| 29 |
+
"name_or_path": "microsoft/DialoGPT-small",
|
| 30 |
+
"errors": "replace",
|
| 31 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 32 |
+
"chat_template": "{% for message in messages %}{{ message.content }}{{ eos_token }}{% endfor %}"
|
| 33 |
+
}
|