Text Generation
Transformers
PyTorch
mistral
Not-For-All-Audiences
nsfw
text-generation-inference
Inference Endpoints
Update tokenizer_config.json
Browse files- tokenizer_config.json +33 -5
tokenizer_config.json
CHANGED
|
@@ -1,9 +1,11 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
"content": "<unk>",
|
| 5 |
"lstrip": false,
|
| 6 |
-
"normalized":
|
| 7 |
"rstrip": false,
|
| 8 |
"single_word": false,
|
| 9 |
"special": true
|
|
@@ -11,7 +13,7 @@
|
|
| 11 |
"1": {
|
| 12 |
"content": "<s>",
|
| 13 |
"lstrip": false,
|
| 14 |
-
"normalized":
|
| 15 |
"rstrip": false,
|
| 16 |
"single_word": false,
|
| 17 |
"special": true
|
|
@@ -23,19 +25,45 @@
|
|
| 23 |
"rstrip": false,
|
| 24 |
"single_word": false,
|
| 25 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
}
|
| 27 |
},
|
| 28 |
"additional_special_tokens": [
|
| 29 |
"<unk>",
|
| 30 |
"<s>",
|
| 31 |
-
"</s>"
|
|
|
|
|
|
|
| 32 |
],
|
| 33 |
"bos_token": "<s>",
|
| 34 |
"clean_up_tokenization_spaces": false,
|
| 35 |
-
"eos_token": "
|
| 36 |
"legacy": true,
|
| 37 |
"model_max_length": 1000000000000000019884624838656,
|
| 38 |
-
"pad_token":
|
| 39 |
"sp_model_kwargs": {},
|
| 40 |
"spaces_between_special_tokens": false,
|
| 41 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"0": {
|
| 6 |
"content": "<unk>",
|
| 7 |
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false,
|
| 11 |
"special": true
|
|
|
|
| 13 |
"1": {
|
| 14 |
"content": "<s>",
|
| 15 |
"lstrip": false,
|
| 16 |
+
"normalized": true,
|
| 17 |
"rstrip": false,
|
| 18 |
"single_word": false,
|
| 19 |
"special": true
|
|
|
|
| 25 |
"rstrip": false,
|
| 26 |
"single_word": false,
|
| 27 |
"special": true
|
| 28 |
+
},
|
| 29 |
+
"32000": {
|
| 30 |
+
"content": "<|im_end|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": true,
|
| 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 |
+
"32002": {
|
| 46 |
+
"content": "[PAD]",
|
| 47 |
+
"lstrip": true,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": true,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
}
|
| 53 |
},
|
| 54 |
"additional_special_tokens": [
|
| 55 |
"<unk>",
|
| 56 |
"<s>",
|
| 57 |
+
"</s>",
|
| 58 |
+
"<|im_end|>",
|
| 59 |
+
"<|im_start|>"
|
| 60 |
],
|
| 61 |
"bos_token": "<s>",
|
| 62 |
"clean_up_tokenization_spaces": false,
|
| 63 |
+
"eos_token": "<|im_end|>",
|
| 64 |
"legacy": true,
|
| 65 |
"model_max_length": 1000000000000000019884624838656,
|
| 66 |
+
"pad_token": "[PAD]",
|
| 67 |
"sp_model_kwargs": {},
|
| 68 |
"spaces_between_special_tokens": false,
|
| 69 |
"tokenizer_class": "LlamaTokenizer",
|