Commit
•
78df6d3
1
Parent(s):
9e25499
Upload 3 files
Browse files- special_tokens_map.json +7 -21
- tokenizer.json +0 -0
- tokenizer_config.json +7 -33
special_tokens_map.json
CHANGED
|
@@ -1,23 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
"eos_token": {
|
| 10 |
-
"content": "</s>",
|
| 11 |
-
"lstrip": false,
|
| 12 |
-
"normalized": false,
|
| 13 |
-
"rstrip": false,
|
| 14 |
-
"single_word": false
|
| 15 |
-
},
|
| 16 |
-
"unk_token": {
|
| 17 |
-
"content": "<unk>",
|
| 18 |
-
"lstrip": false,
|
| 19 |
-
"normalized": false,
|
| 20 |
-
"rstrip": false,
|
| 21 |
-
"single_word": false
|
| 22 |
-
}
|
| 23 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>"
|
| 5 |
+
],
|
| 6 |
+
"bos_token": "<|endoftext|>",
|
| 7 |
+
"eos_token": "<|endoftext|>",
|
| 8 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,35 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
},
|
| 10 |
-
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
|
| 11 |
-
"clean_up_tokenization_spaces": false,
|
| 12 |
-
"eos_token": {
|
| 13 |
-
"__type": "AddedToken",
|
| 14 |
-
"content": "</s>",
|
| 15 |
-
"lstrip": false,
|
| 16 |
-
"normalized": false,
|
| 17 |
-
"rstrip": false,
|
| 18 |
-
"single_word": false
|
| 19 |
-
},
|
| 20 |
-
"legacy": false,
|
| 21 |
-
"model_max_length": 1000000000000000019884624838656,
|
| 22 |
-
"pad_token": null,
|
| 23 |
-
"padding_side": "right",
|
| 24 |
-
"sp_model_kwargs": {},
|
| 25 |
-
"tokenizer_class": "LlamaTokenizer",
|
| 26 |
-
"unk_token": {
|
| 27 |
-
"__type": "AddedToken",
|
| 28 |
-
"content": "<unk>",
|
| 29 |
-
"lstrip": false,
|
| 30 |
-
"normalized": false,
|
| 31 |
-
"rstrip": false,
|
| 32 |
-
"single_word": false
|
| 33 |
-
},
|
| 34 |
-
"use_default_system_prompt": true
|
| 35 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<|endoftext|>",
|
| 4 |
+
"clean_up_tokenization_spaces": true,
|
| 5 |
+
"eos_token": "<|endoftext|>",
|
| 6 |
+
"model_max_length": 2048,
|
| 7 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
| 8 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
}
|