MichelNivard
commited on
Commit
•
cad288d
1
Parent(s):
d3e26d6
Upload tokenizer
Browse files- added_tokens.json +3 -0
- special_tokens_map.json +5 -0
- spiece.model +3 -0
- tokenizer_config.json +18 -0
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[PAD]": 32768
|
3 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": "<|endoftext|>",
|
3 |
+
"pad_token": "[PAD]",
|
4 |
+
"unk_token": "<|unk|>"
|
5 |
+
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e1ba8b7df0701723d2d901c7a42182fe77bf0045173f2cdb474ca6ea3eb1c02
|
3 |
+
size 707660
|
tokenizer_config.json
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_map": {
|
3 |
+
"AutoTokenizer": [
|
4 |
+
"replit/replit-code-v1-3b--replit_lm_tokenizer.ReplitLMTokenizer",
|
5 |
+
null
|
6 |
+
]
|
7 |
+
},
|
8 |
+
"bos_token": null,
|
9 |
+
"clean_up_tokenization_spaces": false,
|
10 |
+
"eos_token": "<|endoftext|>",
|
11 |
+
"model_max_length": 2048,
|
12 |
+
"pad_token": "<|pad|>",
|
13 |
+
"padding_side": "right",
|
14 |
+
"sep_token": null,
|
15 |
+
"sp_model_kwargs": {},
|
16 |
+
"tokenizer_class": "ReplitLMTokenizer",
|
17 |
+
"unk_token": "<|unk|>"
|
18 |
+
}
|