Hugging Face's logo

yangwooko
/
santacoder-finetuned-the-stack-v2-verilog

Text Generation
Transformers
Safetensors
gpt2
custom_code
text-generation-inference
Model card Files
xet
Community
yangwooko commited on
Commit
2cc8c6f
·
verified ·
1 Parent(s): e8ddc5f

Training in progress, step 1

Browse files
Files changed (8) hide show
  1. added_tokens.json +7 -0
  2. merges.txt +0 -0
  3. model.safetensors +1 -1
  4. special_tokens_map.json +25 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +60 -0
  7. training_args.bin +1 -1
  8. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "<fim-middle>": 49154,
3
+ "<fim-pad>": 49156,
4
+ "<fim-prefix>": 49153,
5
+ "<fim-suffix>": 49155,
6
+ "<|endoftext|>": 49152
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc956b226ea89abbd39f8efcf6b2115aef2b22f959b146853c9d9314cdb09c15
3
  size 4600250264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e26ab29c17b27a75728a7fb497891bd65fdc1cee1a5ebd34d7a047399965264d
3
  size 4600250264
special_tokens_map.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<fim-prefix>",
5
+ "<fim-middle>",
6
+ "<fim-suffix>",
7
+ "<fim-pad>"
8
+ ],
9
+ "bos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "pad_token": "<|endoftext|>",
24
+ "unk_token": "<|endoftext|>"
25
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "49152": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "49153": {
13
+ "content": "<fim-prefix>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "49154": {
21
+ "content": "<fim-middle>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "49155": {
29
+ "content": "<fim-suffix>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "49156": {
37
+ "content": "<fim-pad>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "additional_special_tokens": [
46
+ "<|endoftext|>",
47
+ "<fim-prefix>",
48
+ "<fim-middle>",
49
+ "<fim-suffix>",
50
+ "<fim-pad>"
51
+ ],
52
+ "bos_token": "<|endoftext|>",
53
+ "clean_up_tokenization_spaces": true,
54
+ "eos_token": "<|endoftext|>",
55
+ "errors": "replace",
56
+ "model_max_length": 2048,
57
+ "pad_token": "<|endoftext|>",
58
+ "tokenizer_class": "GPT2Tokenizer",
59
+ "unk_token": "<|endoftext|>"
60
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ce51bc465276256b1f5feade3ff4e5235bf8adc08d38ad322151cd1a4d4405a7
3
  size 4475
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd1bb658c9c3b54dddec5d6f10ecb19a57d6230bbdc973c48fc39f14425ed1ec
3
  size 4475
vocab.json ADDED
The diff for this file is too large to render. See raw diff