Maninder Singh
commited on
Commit
•
6b14493
1
Parent(s):
a9979f5
uploaded trained model files
Browse filesI have uploaded all the files of Classification model to classify out of 25 programming languages
- config.json +84 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "huggingface/CodeBERTa-small-v1",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "Scala",
|
15 |
+
"1": "JavaScript",
|
16 |
+
"2": "COBOL",
|
17 |
+
"3": "ARM Assembly",
|
18 |
+
"4": "R",
|
19 |
+
"5": "Lua",
|
20 |
+
"6": "C++",
|
21 |
+
"7": "Visual Basic .NET",
|
22 |
+
"8": "Go",
|
23 |
+
"9": "Erlang",
|
24 |
+
"10": "C#",
|
25 |
+
"11": "Rust",
|
26 |
+
"12": "Ruby",
|
27 |
+
"13": "Swift",
|
28 |
+
"14": "Mathematica/Wolfram Language",
|
29 |
+
"15": "PHP",
|
30 |
+
"16": "Fortran",
|
31 |
+
"17": "AppleScript",
|
32 |
+
"18": "Pascal",
|
33 |
+
"19": "Java",
|
34 |
+
"20": "PowerShell",
|
35 |
+
"21": "Python",
|
36 |
+
"22": "C",
|
37 |
+
"23": "Perl",
|
38 |
+
"24": "Kotlin",
|
39 |
+
"25": "jq"
|
40 |
+
},
|
41 |
+
"initializer_range": 0.02,
|
42 |
+
"intermediate_size": 3072,
|
43 |
+
"label2id": {
|
44 |
+
"ARM Assembly": 3,
|
45 |
+
"AppleScript": 17,
|
46 |
+
"C": 22,
|
47 |
+
"C#": 10,
|
48 |
+
"C++": 6,
|
49 |
+
"COBOL": 2,
|
50 |
+
"Erlang": 9,
|
51 |
+
"Fortran": 16,
|
52 |
+
"Go": 8,
|
53 |
+
"Java": 19,
|
54 |
+
"JavaScript": 1,
|
55 |
+
"Kotlin": 24,
|
56 |
+
"Lua": 5,
|
57 |
+
"Mathematica/Wolfram Language": 14,
|
58 |
+
"PHP": 15,
|
59 |
+
"Pascal": 18,
|
60 |
+
"Perl": 23,
|
61 |
+
"PowerShell": 20,
|
62 |
+
"Python": 21,
|
63 |
+
"R": 4,
|
64 |
+
"Ruby": 12,
|
65 |
+
"Rust": 11,
|
66 |
+
"Scala": 0,
|
67 |
+
"Swift": 13,
|
68 |
+
"Visual Basic .NET": 7,
|
69 |
+
"jq": 25
|
70 |
+
},
|
71 |
+
"layer_norm_eps": 1e-05,
|
72 |
+
"max_position_embeddings": 514,
|
73 |
+
"model_type": "roberta",
|
74 |
+
"num_attention_heads": 12,
|
75 |
+
"num_hidden_layers": 6,
|
76 |
+
"pad_token_id": 1,
|
77 |
+
"position_embedding_type": "absolute",
|
78 |
+
"problem_type": "single_label_classification",
|
79 |
+
"torch_dtype": "float32",
|
80 |
+
"transformers_version": "4.36.2",
|
81 |
+
"type_vocab_size": 1,
|
82 |
+
"use_cache": true,
|
83 |
+
"vocab_size": 52000
|
84 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05db74cc2041bdc253966a9c5a171e767951baf7962dd6130b372cac04eb2dd3
|
3 |
+
size 333896024
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"4": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"bos_token": "<s>",
|
46 |
+
"clean_up_tokenization_spaces": true,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
+
"mask_token": "<mask>",
|
51 |
+
"max_len": 512,
|
52 |
+
"model_max_length": 512,
|
53 |
+
"pad_token": "<pad>",
|
54 |
+
"sep_token": "</s>",
|
55 |
+
"tokenizer_class": "RobertaTokenizer",
|
56 |
+
"trim_offsets": true,
|
57 |
+
"unk_token": "<unk>"
|
58 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c48036af989e1b9e4843901c0aae01d2174db734c36980164adf76df423df5f
|
3 |
+
size 4728
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|