update
Browse files- special_tokens_map.json +10 -22
- tokenizer_config.json +1 -1
special_tokens_map.json
CHANGED
|
@@ -1,26 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": [
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
"normalized": false,
|
| 7 |
-
"rstrip": false,
|
| 8 |
-
"single_word": false
|
| 9 |
-
},
|
| 10 |
-
{
|
| 11 |
-
"content": "<|prompter|>",
|
| 12 |
-
"lstrip": false,
|
| 13 |
-
"normalized": false,
|
| 14 |
-
"rstrip": false,
|
| 15 |
-
"single_word": false
|
| 16 |
-
},
|
| 17 |
-
{
|
| 18 |
-
"content": "<|assistant|>",
|
| 19 |
-
"lstrip": false,
|
| 20 |
-
"normalized": false,
|
| 21 |
-
"rstrip": false,
|
| 22 |
-
"single_word": false
|
| 23 |
-
}
|
| 24 |
],
|
| 25 |
"bos_token": {
|
| 26 |
"content": "<s>",
|
|
@@ -36,7 +18,13 @@
|
|
| 36 |
"rstrip": false,
|
| 37 |
"single_word": false
|
| 38 |
},
|
| 39 |
-
"pad_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
"unk_token": {
|
| 41 |
"content": "<unk>",
|
| 42 |
"lstrip": false,
|
|
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": [
|
| 3 |
+
"<|system|>",
|
| 4 |
+
"<|prompter|>",
|
| 5 |
+
"<|assistant|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
],
|
| 7 |
"bos_token": {
|
| 8 |
"content": "<s>",
|
|
|
|
| 18 |
"rstrip": false,
|
| 19 |
"single_word": false
|
| 20 |
},
|
| 21 |
+
"pad_token": {
|
| 22 |
+
"content": "<pad>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false
|
| 27 |
+
},
|
| 28 |
"unk_token": {
|
| 29 |
"content": "<unk>",
|
| 30 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
|
@@ -65,7 +65,7 @@
|
|
| 65 |
"<|assistant|>"
|
| 66 |
],
|
| 67 |
"bos_token": "<s>",
|
| 68 |
-
"chat_template": "{% for message in messages %}
|
| 69 |
"clean_up_tokenization_spaces": false,
|
| 70 |
"eos_token": "</s>",
|
| 71 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
| 65 |
"<|assistant|>"
|
| 66 |
],
|
| 67 |
"bos_token": "<s>",
|
| 68 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '<|prompter|>' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ '<|system|>' + message['content'] + eos_token }}{% elif message['role'] == 'assistant' %}{{ '<|assistant|>' + message['content'] + eos_token }}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|assistant|>' }}{% endif %}{% endfor %}",
|
| 69 |
"clean_up_tokenization_spaces": false,
|
| 70 |
"eos_token": "</s>",
|
| 71 |
"model_max_length": 1000000000000000019884624838656,
|