Commit
•
52d175c
1
Parent(s):
9267c04
End of training
Browse files- added_tokens.json +3 -0
- merges.txt +0 -0
- pytorch_model.bin +1 -1
- special_tokens_map.json +4 -0
- tokenizer.json +0 -0
- tokenizer_config.json +6 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 40478
|
| 3 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 466186517
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7dc1ca4469681105c8acdbf4b4689216da48faf3c32f812a250bfe2749fed72d
|
| 3 |
size 466186517
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pad_token": "[PAD]",
|
| 3 |
+
"unk_token": "<unk>"
|
| 4 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"clean_up_tokenization_spaces": true,
|
| 3 |
+
"model_max_length": 512,
|
| 4 |
+
"tokenizer_class": "OpenAIGPTTokenizer",
|
| 5 |
+
"unk_token": "<unk>"
|
| 6 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|