Update tokenizer_config.json
Browse files- tokenizer_config.json +7 -8
tokenizer_config.json
CHANGED
@@ -28,32 +28,31 @@
|
|
28 |
},
|
29 |
"32000": {
|
30 |
"content": "<|im_end|>",
|
31 |
-
"lstrip":
|
32 |
-
"normalized":
|
33 |
-
"rstrip":
|
34 |
"single_word": false,
|
35 |
-
"special":
|
36 |
},
|
37 |
"32001": {
|
38 |
"content": "<|im_start|>",
|
39 |
"lstrip": true,
|
40 |
-
"normalized":
|
41 |
"rstrip": true,
|
42 |
"single_word": false,
|
43 |
-
"special":
|
44 |
}
|
45 |
},
|
46 |
"additional_special_tokens": [],
|
47 |
"bos_token": "<s>",
|
48 |
"clean_up_tokenization_spaces": false,
|
49 |
-
"eos_token": "
|
50 |
"legacy": true,
|
51 |
"model_max_length": 1000000000000000019884624838656,
|
52 |
"pad_token": null,
|
53 |
"sp_model_kwargs": {},
|
54 |
"spaces_between_special_tokens": false,
|
55 |
"tokenizer_class": "LlamaTokenizer",
|
56 |
-
"tokenizer_file": "/home/wing/.cache/huggingface/hub/models--mistralai--Mistral-7B-v0.1/snapshots/78814a934d8ce59ee93599378f3e929ff137da06/tokenizer.json",
|
57 |
"trust_remote_code": false,
|
58 |
"unk_token": "<unk>",
|
59 |
"use_default_system_prompt": true,
|
|
|
28 |
},
|
29 |
"32000": {
|
30 |
"content": "<|im_end|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
"single_word": false,
|
35 |
+
"special": true
|
36 |
},
|
37 |
"32001": {
|
38 |
"content": "<|im_start|>",
|
39 |
"lstrip": true,
|
40 |
+
"normalized": false,
|
41 |
"rstrip": true,
|
42 |
"single_word": false,
|
43 |
+
"special": true
|
44 |
}
|
45 |
},
|
46 |
"additional_special_tokens": [],
|
47 |
"bos_token": "<s>",
|
48 |
"clean_up_tokenization_spaces": false,
|
49 |
+
"eos_token": "<|im_end|>",
|
50 |
"legacy": true,
|
51 |
"model_max_length": 1000000000000000019884624838656,
|
52 |
"pad_token": null,
|
53 |
"sp_model_kwargs": {},
|
54 |
"spaces_between_special_tokens": false,
|
55 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
56 |
"trust_remote_code": false,
|
57 |
"unk_token": "<unk>",
|
58 |
"use_default_system_prompt": true,
|