Add files using upload-large-folder tool
Browse files- added_tokens.json +1 -2
- special_tokens_map.json +1 -1
- tokenizer.json +2 -2
- tokenizer_config.json +10 -10
added_tokens.json
CHANGED
|
@@ -9,6 +9,5 @@
|
|
| 9 |
"<|tool_response|>": 200027,
|
| 10 |
"<|tool|>": 200023,
|
| 11 |
"<|user|>": 200021,
|
| 12 |
-
"<|PAD▁TOKEN|>":
|
| 13 |
-
"�": 200029
|
| 14 |
}
|
|
|
|
| 9 |
"<|tool_response|>": 200027,
|
| 10 |
"<|tool|>": 200023,
|
| 11 |
"<|user|>": 200021,
|
| 12 |
+
"<|PAD▁TOKEN|>": 200029
|
|
|
|
| 13 |
}
|
special_tokens_map.json
CHANGED
|
@@ -14,5 +14,5 @@
|
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
"pad_token": "<|PAD▁TOKEN|>",
|
| 17 |
-
"unk_token": "
|
| 18 |
}
|
|
|
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
"pad_token": "<|PAD▁TOKEN|>",
|
| 17 |
+
"unk_token": "�"
|
| 18 |
}
|
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 sha256:37b10016a39382ff2d24acc20a291ed83243a26c4549ab01f6240e72c6291d56
|
| 3 |
+
size 15524472
|
tokenizer_config.json
CHANGED
|
@@ -3,6 +3,14 @@
|
|
| 3 |
"add_eos_token": false,
|
| 4 |
"add_prefix_space": false,
|
| 5 |
"added_tokens_decoder": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
"199999": {
|
| 7 |
"content": "<|endoftext|>",
|
| 8 |
"lstrip": false,
|
|
@@ -100,14 +108,6 @@
|
|
| 100 |
"special": true
|
| 101 |
},
|
| 102 |
"200029": {
|
| 103 |
-
"content": "�",
|
| 104 |
-
"lstrip": false,
|
| 105 |
-
"normalized": false,
|
| 106 |
-
"rstrip": false,
|
| 107 |
-
"single_word": false,
|
| 108 |
-
"special": true
|
| 109 |
-
},
|
| 110 |
-
"200030": {
|
| 111 |
"content": "<|PAD▁TOKEN|>",
|
| 112 |
"lstrip": false,
|
| 113 |
"normalized": false,
|
|
@@ -117,7 +117,7 @@
|
|
| 117 |
}
|
| 118 |
},
|
| 119 |
"bos_token": "<|endoftext|>",
|
| 120 |
-
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{%
|
| 121 |
"clean_up_tokenization_spaces": false,
|
| 122 |
"eos_token": "<|endoftext|>",
|
| 123 |
"extra_special_tokens": {},
|
|
@@ -125,5 +125,5 @@
|
|
| 125 |
"pad_token": "<|PAD▁TOKEN|>",
|
| 126 |
"padding_side": "left",
|
| 127 |
"tokenizer_class": "GPT2Tokenizer",
|
| 128 |
-
"unk_token": "
|
| 129 |
}
|
|
|
|
| 3 |
"add_eos_token": false,
|
| 4 |
"add_prefix_space": false,
|
| 5 |
"added_tokens_decoder": {
|
| 6 |
+
"3251": {
|
| 7 |
+
"content": "�",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
"199999": {
|
| 15 |
"content": "<|endoftext|>",
|
| 16 |
"lstrip": false,
|
|
|
|
| 108 |
"special": true
|
| 109 |
},
|
| 110 |
"200029": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 111 |
"content": "<|PAD▁TOKEN|>",
|
| 112 |
"lstrip": false,
|
| 113 |
"normalized": false,
|
|
|
|
| 117 |
}
|
| 118 |
},
|
| 119 |
"bos_token": "<|endoftext|>",
|
| 120 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% endif %}",
|
| 121 |
"clean_up_tokenization_spaces": false,
|
| 122 |
"eos_token": "<|endoftext|>",
|
| 123 |
"extra_special_tokens": {},
|
|
|
|
| 125 |
"pad_token": "<|PAD▁TOKEN|>",
|
| 126 |
"padding_side": "left",
|
| 127 |
"tokenizer_class": "GPT2Tokenizer",
|
| 128 |
+
"unk_token": "�"
|
| 129 |
}
|