Commit
•
15097b8
1
Parent(s):
86e7dee
Upload tokenizer
Browse files- .gitattributes +1 -0
- special_tokens_map.json +6 -0
- tokenizer.json +3 -0
- tokenizer_config.json +11 -0
.gitattributes
CHANGED
|
@@ -17,3 +17,4 @@ runs/Jun04_02-06-39_4367d7224c9f/events.out.tfevents.1685845095.4367d7224c9f.857
|
|
| 17 |
runs/Jun04_13-23-35_1c0366a2fd20/1685885434.1947937/events.out.tfevents.1685885434.1c0366a2fd20.848.1 filter=lfs diff=lfs merge=lfs -text
|
| 18 |
runs/Jun04_13-23-35_1c0366a2fd20/events.out.tfevents.1685885434.1c0366a2fd20.848.0 filter=lfs diff=lfs merge=lfs -text
|
| 19 |
adapter_model.bin filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 17 |
runs/Jun04_13-23-35_1c0366a2fd20/1685885434.1947937/events.out.tfevents.1685885434.1c0366a2fd20.848.1 filter=lfs diff=lfs merge=lfs -text
|
| 18 |
runs/Jun04_13-23-35_1c0366a2fd20/events.out.tfevents.1685885434.1c0366a2fd20.848.0 filter=lfs diff=lfs merge=lfs -text
|
| 19 |
adapter_model.bin filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
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 sha256:17a208233d2ee8d8c83b23bc214df737c44806a1919f444e89b31e586cd956ba
|
| 3 |
+
size 14500471
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"clean_up_tokenization_spaces": false,
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 7 |
+
"pad_token": "<pad>",
|
| 8 |
+
"padding_side": "left",
|
| 9 |
+
"tokenizer_class": "BloomTokenizer",
|
| 10 |
+
"unk_token": "<unk>"
|
| 11 |
+
}
|