Upload tokenizer
Browse files- tokenizer_config.json +34 -4
tokenizer_config.json
CHANGED
|
@@ -1,4 +1,6 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
"content": "<unk>",
|
|
@@ -25,16 +27,44 @@
|
|
| 25 |
"special": true
|
| 26 |
}
|
| 27 |
},
|
| 28 |
-
"bos_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
| 30 |
"clean_up_tokenization_spaces": false,
|
| 31 |
-
"eos_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
"legacy": false,
|
| 33 |
"model_max_length": 2048,
|
| 34 |
-
"pad_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 35 |
"padding_side": "right",
|
| 36 |
"sp_model_kwargs": {},
|
| 37 |
"tokenizer_class": "LlamaTokenizer",
|
| 38 |
-
"unk_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
"use_default_system_prompt": false
|
| 40 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"0": {
|
| 6 |
"content": "<unk>",
|
|
|
|
| 27 |
"special": true
|
| 28 |
}
|
| 29 |
},
|
| 30 |
+
"bos_token": {
|
| 31 |
+
"__type": "AddedToken",
|
| 32 |
+
"content": "<s>",
|
| 33 |
+
"lstrip": false,
|
| 34 |
+
"normalized": true,
|
| 35 |
+
"rstrip": false,
|
| 36 |
+
"single_word": false
|
| 37 |
+
},
|
| 38 |
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
| 39 |
"clean_up_tokenization_spaces": false,
|
| 40 |
+
"eos_token": {
|
| 41 |
+
"__type": "AddedToken",
|
| 42 |
+
"content": "</s>",
|
| 43 |
+
"lstrip": false,
|
| 44 |
+
"normalized": true,
|
| 45 |
+
"rstrip": false,
|
| 46 |
+
"single_word": false
|
| 47 |
+
},
|
| 48 |
"legacy": false,
|
| 49 |
"model_max_length": 2048,
|
| 50 |
+
"pad_token": {
|
| 51 |
+
"__type": "AddedToken",
|
| 52 |
+
"content": "</s>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": true,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false
|
| 57 |
+
},
|
| 58 |
"padding_side": "right",
|
| 59 |
"sp_model_kwargs": {},
|
| 60 |
"tokenizer_class": "LlamaTokenizer",
|
| 61 |
+
"unk_token": {
|
| 62 |
+
"__type": "AddedToken",
|
| 63 |
+
"content": "<unk>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": true,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false
|
| 68 |
+
},
|
| 69 |
"use_default_system_prompt": false
|
| 70 |
}
|