Apply @unsloth tokenizer fixes
Browse files- README.md +1 -0
- generation_config.json +3 -6
- special_tokens_map.json +2 -9
- tokenizer_config.json +14 -4
README.md
CHANGED
|
@@ -30,6 +30,7 @@ pipeline_tag: text-generation
|
|
| 30 |
tags:
|
| 31 |
- nlp
|
| 32 |
- code
|
|
|
|
| 33 |
widget:
|
| 34 |
- messages:
|
| 35 |
- role: user
|
|
|
|
| 30 |
tags:
|
| 31 |
- nlp
|
| 32 |
- code
|
| 33 |
+
- abliterated
|
| 34 |
widget:
|
| 35 |
- messages:
|
| 36 |
- role: user
|
generation_config.json
CHANGED
|
@@ -1,10 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 199999,
|
| 4 |
-
"eos_token_id":
|
| 5 |
-
|
| 6 |
-
199999
|
| 7 |
-
],
|
| 8 |
-
"pad_token_id": 199999,
|
| 9 |
"transformers_version": "4.45.0"
|
| 10 |
-
}
|
|
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 199999,
|
| 4 |
+
"eos_token_id": 200020,
|
| 5 |
+
"pad_token_id": 200029,
|
|
|
|
|
|
|
|
|
|
| 6 |
"transformers_version": "4.45.0"
|
| 7 |
+
}
|
special_tokens_map.json
CHANGED
|
@@ -7,21 +7,14 @@
|
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"eos_token": {
|
| 10 |
-
"content": "<|
|
| 11 |
"lstrip": false,
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
"pad_token": {
|
| 17 |
-
"content": "<|
|
| 18 |
-
"lstrip": false,
|
| 19 |
-
"normalized": false,
|
| 20 |
-
"rstrip": false,
|
| 21 |
-
"single_word": false
|
| 22 |
-
},
|
| 23 |
-
"unk_token": {
|
| 24 |
-
"content": "<|endoftext|>",
|
| 25 |
"lstrip": false,
|
| 26 |
"normalized": false,
|
| 27 |
"rstrip": false,
|
|
|
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"eos_token": {
|
| 10 |
+
"content": "<|end|>",
|
| 11 |
"lstrip": false,
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
"pad_token": {
|
| 17 |
+
"content": "<|PAD_TOKEN|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
"lstrip": false,
|
| 19 |
"normalized": false,
|
| 20 |
"rstrip": false,
|
tokenizer_config.json
CHANGED
|
@@ -98,14 +98,24 @@
|
|
| 98 |
"rstrip": true,
|
| 99 |
"single_word": false,
|
| 100 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 101 |
}
|
| 102 |
},
|
| 103 |
"bos_token": "<|endoftext|>",
|
| 104 |
-
"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|>' }}{%
|
| 105 |
"clean_up_tokenization_spaces": false,
|
| 106 |
-
"eos_token": "<|
|
|
|
|
| 107 |
"model_max_length": 131072,
|
| 108 |
-
"pad_token": "<|
|
|
|
|
| 109 |
"tokenizer_class": "GPT2Tokenizer",
|
| 110 |
-
"unk_token": "
|
| 111 |
}
|
|
|
|
| 98 |
"rstrip": true,
|
| 99 |
"single_word": false,
|
| 100 |
"special": true
|
| 101 |
+
},
|
| 102 |
+
"200029": {
|
| 103 |
+
"content": "<|PAD▁TOKEN|>",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": false,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": true
|
| 109 |
}
|
| 110 |
},
|
| 111 |
"bos_token": "<|endoftext|>",
|
| 112 |
+
"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 %}",
|
| 113 |
"clean_up_tokenization_spaces": false,
|
| 114 |
+
"eos_token": "<|end|>",
|
| 115 |
+
"extra_special_tokens": {},
|
| 116 |
"model_max_length": 131072,
|
| 117 |
+
"pad_token": "<|PAD_TOKEN|>",
|
| 118 |
+
"padding_side": "left",
|
| 119 |
"tokenizer_class": "GPT2Tokenizer",
|
| 120 |
+
"unk_token": "�"
|
| 121 |
}
|