Upload tokenizer
Browse files- special_tokens_map.json +1 -7
- tokenizer_config.json +1 -1
special_tokens_map.json
CHANGED
@@ -18,13 +18,7 @@
|
|
18 |
"rstrip": false,
|
19 |
"single_word": false
|
20 |
},
|
21 |
-
"eos_token":
|
22 |
-
"content": "<|im_end|>",
|
23 |
-
"lstrip": false,
|
24 |
-
"normalized": false,
|
25 |
-
"rstrip": false,
|
26 |
-
"single_word": false
|
27 |
-
},
|
28 |
"pad_token": "<pad>",
|
29 |
"unk_token": {
|
30 |
"content": "<|endoftext|>",
|
|
|
18 |
"rstrip": false,
|
19 |
"single_word": false
|
20 |
},
|
21 |
+
"eos_token": "<eos>",
|
|
|
|
|
|
|
|
|
|
|
|
|
22 |
"pad_token": "<pad>",
|
23 |
"unk_token": {
|
24 |
"content": "<|endoftext|>",
|
tokenizer_config.json
CHANGED
@@ -233,7 +233,7 @@
|
|
233 |
"bos_token": "<|im_start|>",
|
234 |
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
235 |
"clean_up_tokenization_spaces": false,
|
236 |
-
"eos_token": "
|
237 |
"extra_special_tokens": {},
|
238 |
"model_max_length": 8192,
|
239 |
"pad_token": "<pad>",
|
|
|
233 |
"bos_token": "<|im_start|>",
|
234 |
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
235 |
"clean_up_tokenization_spaces": false,
|
236 |
+
"eos_token": "<eos>",
|
237 |
"extra_special_tokens": {},
|
238 |
"model_max_length": 8192,
|
239 |
"pad_token": "<pad>",
|