whizzzzkid
commited on
Commit
•
c419b47
1
Parent(s):
99cdc22
Upload tokenizer
Browse files- tokenizer.json +2 -2
- tokenizer_config.json +4 -0
tokenizer.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:290f60278265b590e6e79137d425f9aa8c19d934e08b6ac7a6229e55a1bdaa27
|
3 |
+
size 4239524
|
tokenizer_config.json
CHANGED
@@ -305,8 +305,12 @@
|
|
305 |
"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 %}",
|
306 |
"clean_up_tokenization_spaces": true,
|
307 |
"eos_token": "<|endoftext|>",
|
|
|
308 |
"model_max_length": 2048,
|
309 |
"pad_token": "<|endoftext|>",
|
|
|
310 |
"tokenizer_class": "GPT2Tokenizer",
|
|
|
|
|
311 |
"unk_token": "<|endoftext|>"
|
312 |
}
|
|
|
305 |
"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 %}",
|
306 |
"clean_up_tokenization_spaces": true,
|
307 |
"eos_token": "<|endoftext|>",
|
308 |
+
"max_length": 2048,
|
309 |
"model_max_length": 2048,
|
310 |
"pad_token": "<|endoftext|>",
|
311 |
+
"stride": 0,
|
312 |
"tokenizer_class": "GPT2Tokenizer",
|
313 |
+
"truncation_side": "right",
|
314 |
+
"truncation_strategy": "longest_first",
|
315 |
"unk_token": "<|endoftext|>"
|
316 |
}
|