Update tokenizer_config.json (#4)
Browse files- Upload tokenizer_config.json (263d7ce5e63f267f17db7a12c4b89f14c990b67f)
- Update tokenizer_config.json (72d02df0c343329511e796e7e67b5dbbf4a191fa)
- Update special_tokens_map.json (f7f8f66ce688863cfbe19514484a2f2b82080926)
Co-authored-by: minyi <minyichen@users.noreply.huggingface.co>
- special_tokens_map.json +1 -1
- tokenizer_config.json +2 -2
special_tokens_map.json
CHANGED
|
@@ -7,7 +7,7 @@
|
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"eos_token": {
|
| 10 |
-
"content": "<|
|
| 11 |
"lstrip": false,
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
|
|
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"eos_token": {
|
| 10 |
+
"content": "<|eot_id|>",
|
| 11 |
"lstrip": false,
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
tokenizer_config.json
CHANGED
|
@@ -2066,9 +2066,9 @@
|
|
| 2066 |
}
|
| 2067 |
},
|
| 2068 |
"bos_token": "<|begin_of_text|>",
|
| 2069 |
-
"chat_template": "{%
|
| 2070 |
"clean_up_tokenization_spaces": true,
|
| 2071 |
-
"eos_token": "<|
|
| 2072 |
"model_input_names": [
|
| 2073 |
"input_ids",
|
| 2074 |
"attention_mask"
|
|
|
|
| 2066 |
}
|
| 2067 |
},
|
| 2068 |
"bos_token": "<|begin_of_text|>",
|
| 2069 |
+
"chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
| 2070 |
"clean_up_tokenization_spaces": true,
|
| 2071 |
+
"eos_token": "<|eot_id|>",
|
| 2072 |
"model_input_names": [
|
| 2073 |
"input_ids",
|
| 2074 |
"attention_mask"
|