Commit
•
772b643
1
Parent(s):
b519b19
Upload tokenizer
Browse files- special_tokens_map.json +3 -21
- tokenizer_config.json +0 -66
special_tokens_map.json
CHANGED
|
@@ -3,26 +3,8 @@
|
|
| 3 |
"<|im_start|>",
|
| 4 |
"<|im_end|>"
|
| 5 |
],
|
| 6 |
-
"bos_token":
|
| 7 |
-
|
| 8 |
-
"lstrip": false,
|
| 9 |
-
"normalized": false,
|
| 10 |
-
"rstrip": false,
|
| 11 |
-
"single_word": false
|
| 12 |
-
},
|
| 13 |
-
"eos_token": {
|
| 14 |
-
"content": "<|endoftext|>",
|
| 15 |
-
"lstrip": false,
|
| 16 |
-
"normalized": false,
|
| 17 |
-
"rstrip": false,
|
| 18 |
-
"single_word": false
|
| 19 |
-
},
|
| 20 |
"pad_token": "<|pad|>",
|
| 21 |
-
"unk_token":
|
| 22 |
-
"content": "<|endoftext|>",
|
| 23 |
-
"lstrip": false,
|
| 24 |
-
"normalized": false,
|
| 25 |
-
"rstrip": false,
|
| 26 |
-
"single_word": false
|
| 27 |
-
}
|
| 28 |
}
|
|
|
|
| 3 |
"<|im_start|>",
|
| 4 |
"<|im_end|>"
|
| 5 |
],
|
| 6 |
+
"bos_token": "<|endoftext|>",
|
| 7 |
+
"eos_token": "<|endoftext|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
"pad_token": "<|pad|>",
|
| 9 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
}
|
tokenizer_config.json
CHANGED
|
@@ -2,72 +2,6 @@
|
|
| 2 |
"add_bos_token": false,
|
| 3 |
"add_eos_token": false,
|
| 4 |
"add_prefix_space": false,
|
| 5 |
-
"added_tokens_decoder": {
|
| 6 |
-
"100257": {
|
| 7 |
-
"content": "<|endoftext|>",
|
| 8 |
-
"lstrip": false,
|
| 9 |
-
"normalized": false,
|
| 10 |
-
"rstrip": false,
|
| 11 |
-
"single_word": false,
|
| 12 |
-
"special": true
|
| 13 |
-
},
|
| 14 |
-
"100258": {
|
| 15 |
-
"content": "<|fim_prefix|>",
|
| 16 |
-
"lstrip": false,
|
| 17 |
-
"normalized": false,
|
| 18 |
-
"rstrip": false,
|
| 19 |
-
"single_word": false,
|
| 20 |
-
"special": true
|
| 21 |
-
},
|
| 22 |
-
"100259": {
|
| 23 |
-
"content": "<|fim_middle|>",
|
| 24 |
-
"lstrip": false,
|
| 25 |
-
"normalized": false,
|
| 26 |
-
"rstrip": false,
|
| 27 |
-
"single_word": false,
|
| 28 |
-
"special": true
|
| 29 |
-
},
|
| 30 |
-
"100260": {
|
| 31 |
-
"content": "<|fim_suffix|>",
|
| 32 |
-
"lstrip": false,
|
| 33 |
-
"normalized": false,
|
| 34 |
-
"rstrip": false,
|
| 35 |
-
"single_word": false,
|
| 36 |
-
"special": true
|
| 37 |
-
},
|
| 38 |
-
"100276": {
|
| 39 |
-
"content": "<|endofprompt|>",
|
| 40 |
-
"lstrip": false,
|
| 41 |
-
"normalized": false,
|
| 42 |
-
"rstrip": false,
|
| 43 |
-
"single_word": false,
|
| 44 |
-
"special": true
|
| 45 |
-
},
|
| 46 |
-
"100277": {
|
| 47 |
-
"content": "<|pad|>",
|
| 48 |
-
"lstrip": false,
|
| 49 |
-
"normalized": false,
|
| 50 |
-
"rstrip": false,
|
| 51 |
-
"single_word": false,
|
| 52 |
-
"special": true
|
| 53 |
-
},
|
| 54 |
-
"100278": {
|
| 55 |
-
"content": "<|im_start|>",
|
| 56 |
-
"lstrip": false,
|
| 57 |
-
"normalized": false,
|
| 58 |
-
"rstrip": false,
|
| 59 |
-
"single_word": false,
|
| 60 |
-
"special": true
|
| 61 |
-
},
|
| 62 |
-
"100279": {
|
| 63 |
-
"content": "<|im_end|>",
|
| 64 |
-
"lstrip": false,
|
| 65 |
-
"normalized": false,
|
| 66 |
-
"rstrip": false,
|
| 67 |
-
"single_word": false,
|
| 68 |
-
"special": true
|
| 69 |
-
}
|
| 70 |
-
},
|
| 71 |
"additional_special_tokens": [
|
| 72 |
"<|im_start|>",
|
| 73 |
"<|im_end|>"
|
|
|
|
| 2 |
"add_bos_token": false,
|
| 3 |
"add_eos_token": false,
|
| 4 |
"add_prefix_space": false,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"additional_special_tokens": [
|
| 6 |
"<|im_start|>",
|
| 7 |
"<|im_end|>"
|