Edison
commited on
Commit
•
bebbe6d
1
Parent(s):
a86bcc6
Training in progress, epoch 1
Browse files- .gitignore +1 -0
- added_tokens.json +6 -0
- config.json +34 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +31 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
added_tokens.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<cls>": 49154,
|
3 |
+
"<mask>": 49155,
|
4 |
+
"<pad>": 49153,
|
5 |
+
"<sep>": 49152
|
6 |
+
}
|
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bigcode/starencoder",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "not_vulnerable",
|
13 |
+
"1": "vulnerable"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 3072,
|
17 |
+
"label2id": {
|
18 |
+
"not_vulnerable": 0,
|
19 |
+
"vulnerable": 1
|
20 |
+
},
|
21 |
+
"layer_norm_eps": 1e-12,
|
22 |
+
"max_position_embeddings": 1024,
|
23 |
+
"model_type": "bert",
|
24 |
+
"num_attention_heads": 12,
|
25 |
+
"num_hidden_layers": 12,
|
26 |
+
"pad_token_id": 49152,
|
27 |
+
"position_embedding_type": "absolute",
|
28 |
+
"problem_type": "single_label_classification",
|
29 |
+
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.31.0",
|
31 |
+
"type_vocab_size": 2,
|
32 |
+
"use_cache": true,
|
33 |
+
"vocab_size": 49156
|
34 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:396cd920db14bd6b90be6b8000334b567ef0642ef8dea99254f2ffbdf7d38d0e
|
3 |
+
size 496820462
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|endoftext|>",
|
4 |
+
"<fim_prefix>",
|
5 |
+
"<fim_middle>",
|
6 |
+
"<fim_suffix>",
|
7 |
+
"<fim_pad>",
|
8 |
+
"<filename>",
|
9 |
+
"<gh_stars>",
|
10 |
+
"<issue_start>",
|
11 |
+
"<issue_comment>",
|
12 |
+
"<issue_closed>",
|
13 |
+
"<jupyter_start>",
|
14 |
+
"<jupyter_text>",
|
15 |
+
"<jupyter_code>",
|
16 |
+
"<jupyter_output>",
|
17 |
+
"<empty_output>",
|
18 |
+
"<commit_before>",
|
19 |
+
"<commit_msg>",
|
20 |
+
"<commit_after>",
|
21 |
+
"<reponame>"
|
22 |
+
],
|
23 |
+
"bos_token": "<|endoftext|>",
|
24 |
+
"cls_token": "<cls>",
|
25 |
+
"eos_token": "<|endoftext|>",
|
26 |
+
"mask_token": "<mask>",
|
27 |
+
"pad_token": "<pad>",
|
28 |
+
"sep_token": "<sep>",
|
29 |
+
"unk_token": "<|endoftext|>"
|
30 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"additional_special_tokens": [
|
4 |
+
"<|endoftext|>",
|
5 |
+
"<fim_prefix>",
|
6 |
+
"<fim_middle>",
|
7 |
+
"<fim_suffix>",
|
8 |
+
"<fim_pad>",
|
9 |
+
"<filename>",
|
10 |
+
"<gh_stars>",
|
11 |
+
"<issue_start>",
|
12 |
+
"<issue_comment>",
|
13 |
+
"<issue_closed>",
|
14 |
+
"<jupyter_start>",
|
15 |
+
"<jupyter_text>",
|
16 |
+
"<jupyter_code>",
|
17 |
+
"<jupyter_output>",
|
18 |
+
"<empty_output>",
|
19 |
+
"<commit_before>",
|
20 |
+
"<commit_msg>",
|
21 |
+
"<commit_after>",
|
22 |
+
"<reponame>"
|
23 |
+
],
|
24 |
+
"bos_token": "<|endoftext|>",
|
25 |
+
"clean_up_tokenization_spaces": true,
|
26 |
+
"eos_token": "<|endoftext|>",
|
27 |
+
"model_max_length": 1000000000000000019884624838656,
|
28 |
+
"tokenizer_class": "GPT2Tokenizer",
|
29 |
+
"unk_token": "<|endoftext|>",
|
30 |
+
"vocab_size": 49152
|
31 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d8cf85195d0904bd9bcd0f7e867c4bbc5b1e743b90986368a734048338bb15f
|
3 |
+
size 4472
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|