Upload model trained with Unsloth
Browse filesUpload model trained with Unsloth 2x faster
- special_tokens_map.json +3 -21
- tokenizer.json +1 -1
- tokenizer_config.json +5 -10
special_tokens_map.json
CHANGED
|
@@ -1,23 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token":
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
"normalized": false,
|
| 6 |
-
"rstrip": false,
|
| 7 |
-
"single_word": false
|
| 8 |
-
},
|
| 9 |
-
"eos_token": {
|
| 10 |
-
"content": "<|eot_id|>",
|
| 11 |
-
"lstrip": false,
|
| 12 |
-
"normalized": false,
|
| 13 |
-
"rstrip": false,
|
| 14 |
-
"single_word": false
|
| 15 |
-
},
|
| 16 |
-
"pad_token": {
|
| 17 |
-
"content": "<|finetune_right_pad_id|>",
|
| 18 |
-
"lstrip": false,
|
| 19 |
-
"normalized": false,
|
| 20 |
-
"rstrip": false,
|
| 21 |
-
"single_word": false
|
| 22 |
-
}
|
| 23 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": "<|begin_of_text|>",
|
| 3 |
+
"eos_token": "<|im_end|>",
|
| 4 |
+
"pad_token": "<|finetune_right_pad_id|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
}
|
tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 17209920
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a113717b4505b4f56b3bc1032540fa90b686c05b875e25bac0e1825441f38984
|
| 3 |
size 17209920
|
tokenizer_config.json
CHANGED
|
@@ -73,7 +73,7 @@
|
|
| 73 |
"special": true
|
| 74 |
},
|
| 75 |
"128009": {
|
| 76 |
-
"content": "<|
|
| 77 |
"lstrip": false,
|
| 78 |
"normalized": false,
|
| 79 |
"rstrip": false,
|
|
@@ -2050,17 +2050,12 @@
|
|
| 2050 |
}
|
| 2051 |
},
|
| 2052 |
"bos_token": "<|begin_of_text|>",
|
| 2053 |
-
"chat_template": "{
|
| 2054 |
-
"clean_up_tokenization_spaces":
|
| 2055 |
-
"eos_token": "<|
|
| 2056 |
"extra_special_tokens": {},
|
| 2057 |
-
"
|
| 2058 |
-
"input_ids",
|
| 2059 |
-
"attention_mask"
|
| 2060 |
-
],
|
| 2061 |
-
"model_max_length": 131072,
|
| 2062 |
"pad_token": "<|finetune_right_pad_id|>",
|
| 2063 |
-
"padding_side": "right",
|
| 2064 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 2065 |
"unk_token": null
|
| 2066 |
}
|
|
|
|
| 73 |
"special": true
|
| 74 |
},
|
| 75 |
"128009": {
|
| 76 |
+
"content": "<|im_end|>",
|
| 77 |
"lstrip": false,
|
| 78 |
"normalized": false,
|
| 79 |
"rstrip": false,
|
|
|
|
| 2050 |
}
|
| 2051 |
},
|
| 2052 |
"bos_token": "<|begin_of_text|>",
|
| 2053 |
+
"chat_template": "{% if 'role' in messages[0] %}{% for message in messages %}{% if message['role'] == 'user' %}{{'<|im_start|>user\n' + message['content'] + '<|im_end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|im_start|>assistant\n' + message['content'] + '<|im_end|>\n' }}{% else %}{{ '<|im_start|>system\n' + message['content'] + '<|im_end|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}{% else %}{% for message in messages %}{% if message['from'] == 'human' %}{{'<|im_start|>user\n' + message['value'] + '<|im_end|>\n'}}{% elif message['from'] == 'gpt' %}{{'<|im_start|>assistant\n' + message['value'] + '<|im_end|>\n' }}{% else %}{{ '<|im_start|>system\n' + message['value'] + '<|im_end|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}{% endif %}",
|
| 2054 |
+
"clean_up_tokenization_spaces": false,
|
| 2055 |
+
"eos_token": "<|im_end|>",
|
| 2056 |
"extra_special_tokens": {},
|
| 2057 |
+
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2058 |
"pad_token": "<|finetune_right_pad_id|>",
|
|
|
|
| 2059 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 2060 |
"unk_token": null
|
| 2061 |
}
|