add tokenizer
Browse files- .gitattributes +1 -0
- special_tokens_map.json +6 -0
- tokenizer.json +3 -0
- tokenizer_config.json +11 -0
.gitattributes
CHANGED
|
@@ -30,3 +30,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 30 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 31 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 32 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 30 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 31 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 32 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"pad_token": "<pad>",
|
| 5 |
+
"unk_token": "<unk>"
|
| 6 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f6efc66e73f1fd69da4f436e48befb519fdff3fe18910850c1d41bd862293a5
|
| 3 |
+
size 14500443
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"name_or_path": "bigscience/bloom-560m",
|
| 6 |
+
"pad_token": "<pad>",
|
| 7 |
+
"padding_side": "left",
|
| 8 |
+
"special_tokens_map_file": null,
|
| 9 |
+
"tokenizer_class": "BloomTokenizer",
|
| 10 |
+
"unk_token": "<unk>"
|
| 11 |
+
}
|