Commit ·
57dbdbd
1
Parent(s): 80e5569
End of training
Browse files- added_tokens.json +3 -0
- merges.txt +0 -0
- pytorch_model.bin +1 -1
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +11 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 50257
|
| 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 333970169
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6805b278b46f0f1cf983948b252e3303a54cbd5a1ac44a323418ae1a3d6b7f4
|
| 3 |
size 333970169
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"unk_token": "<|endoftext|>"
|
| 6 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<|endoftext|>",
|
| 4 |
+
"eos_token": "<|endoftext|>",
|
| 5 |
+
"model_max_length": 1024,
|
| 6 |
+
"name_or_path": "distilgpt2",
|
| 7 |
+
"pad_token": "[PAD]",
|
| 8 |
+
"special_tokens_map_file": null,
|
| 9 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 10 |
+
"unk_token": "<|endoftext|>"
|
| 11 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|