anujsahani01
commited on
Commit
•
9257dea
1
Parent(s):
7001755
Training in progress, step 500
Browse files- .gitignore +1 -0
- added_tokens.json +11 -0
- merges.txt +0 -0
- special_tokens_map.json +12 -0
- tokenizer.json +0 -0
- tokenizer_config.json +18 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
added_tokens.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|assistant|>": 49154,
|
3 |
+
"<|end|>": 49155,
|
4 |
+
"<|system|>": 49152,
|
5 |
+
"<|user|>": 49153,
|
6 |
+
"[ASSISTANT]": 49158,
|
7 |
+
"[END]": 49160,
|
8 |
+
"[PAD]": 49156,
|
9 |
+
"[SYSTEM]": 49157,
|
10 |
+
"[USER]": 49159
|
11 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"[SYSTEM]",
|
4 |
+
"[ASSISTANT]",
|
5 |
+
"[USER]",
|
6 |
+
"[END]"
|
7 |
+
],
|
8 |
+
"bos_token": "<|endoftext|>",
|
9 |
+
"eos_token": "<|endoftext|>",
|
10 |
+
"pad_token": "[PAD]",
|
11 |
+
"unk_token": "<|endoftext|>"
|
12 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"additional_special_tokens": [
|
4 |
+
"[SYSTEM]",
|
5 |
+
"[ASSISTANT]",
|
6 |
+
"[USER]",
|
7 |
+
"[END]"
|
8 |
+
],
|
9 |
+
"bos_token": "<|endoftext|>",
|
10 |
+
"clean_up_tokenization_spaces": true,
|
11 |
+
"eos_token": "<|endoftext|>",
|
12 |
+
"model_max_length": 1000,
|
13 |
+
"pad_token": "[PAD]",
|
14 |
+
"return_token_type_ids": false,
|
15 |
+
"tokenizer_class": "GPT2Tokenizer",
|
16 |
+
"unk_token": "<|endoftext|>",
|
17 |
+
"vocab_size": 49152
|
18 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f76bf2cc3126f9ab6669c3ec25d62743fcf906eab0e2b2fed21f94e11961eb3a
|
3 |
+
size 3899
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|