Upload tokenizer
Browse files- added_tokens.json +13 -0
- tokenizer.json +1 -0
- tokenizer.model +3 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|assistant|>": 32001,
|
| 3 |
+
"<|endoftext|>": 32000,
|
| 4 |
+
"<|end|>": 32007,
|
| 5 |
+
"<|placeholder1|>": 32002,
|
| 6 |
+
"<|placeholder2|>": 32003,
|
| 7 |
+
"<|placeholder3|>": 32004,
|
| 8 |
+
"<|placeholder4|>": 32005,
|
| 9 |
+
"<|placeholder5|>": 32008,
|
| 10 |
+
"<|placeholder6|>": 32009,
|
| 11 |
+
"<|system|>": 32006,
|
| 12 |
+
"<|user|>": 32010
|
| 13 |
+
}
|
tokenizer.json
CHANGED
|
@@ -233,6 +233,7 @@
|
|
| 233 |
"end_of_word_suffix": null,
|
| 234 |
"fuse_unk": true,
|
| 235 |
"byte_fallback": true,
|
|
|
|
| 236 |
"vocab": {
|
| 237 |
"<unk>": 0,
|
| 238 |
"<s>": 1,
|
|
|
|
| 233 |
"end_of_word_suffix": null,
|
| 234 |
"fuse_unk": true,
|
| 235 |
"byte_fallback": true,
|
| 236 |
+
"ignore_merges": false,
|
| 237 |
"vocab": {
|
| 238 |
"<unk>": 0,
|
| 239 |
"<s>": 1,
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|