Upload 5 files
Browse files- config.json +133 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +5 -0
config.json
ADDED
@@ -0,0 +1,133 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "../../save/marinda-default-ep0.4-26m/checkpoint-25000",
|
3 |
+
"architectures": [
|
4 |
+
"CodeArtForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"ep_add_linear_projection": true,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "noacc",
|
16 |
+
"1": "base(int)",
|
17 |
+
"2": "base(char)**",
|
18 |
+
"3": "base(char)*",
|
19 |
+
"4": "base(_Bool)",
|
20 |
+
"5": "base(unsigned int)",
|
21 |
+
"6": "base(long unsigned int)",
|
22 |
+
"7": "struct*",
|
23 |
+
"8": "void*",
|
24 |
+
"9": "base(unsigned char)*",
|
25 |
+
"10": "enum",
|
26 |
+
"11": "base(unsigned char)",
|
27 |
+
"12": "base(char)",
|
28 |
+
"13": "base(unsigned int)*",
|
29 |
+
"14": "base(long int)",
|
30 |
+
"15": "base(short int)*",
|
31 |
+
"16": "union*",
|
32 |
+
"17": "subroutine*",
|
33 |
+
"18": "base(long int)*",
|
34 |
+
"19": "base(int)*",
|
35 |
+
"20": "array*",
|
36 |
+
"21": "struct**",
|
37 |
+
"22": "base(long unsigned int)*",
|
38 |
+
"23": "base(double)*",
|
39 |
+
"24": "void**",
|
40 |
+
"25": "base(short unsigned int)",
|
41 |
+
"26": "struct",
|
42 |
+
"27": "base(_Bool)*",
|
43 |
+
"28": "base(char)***",
|
44 |
+
"29": "base(long unsigned int)**",
|
45 |
+
"30": "base(long double)",
|
46 |
+
"31": "struct***",
|
47 |
+
"32": "enum*",
|
48 |
+
"33": "base(unsigned int)**",
|
49 |
+
"34": "base(long double)*",
|
50 |
+
"35": "base(float)*",
|
51 |
+
"36": "base(long long unsigned int)*",
|
52 |
+
"37": "base(short unsigned int)*",
|
53 |
+
"38": "base(signed char)*",
|
54 |
+
"39": "base(long long int)",
|
55 |
+
"40": "array",
|
56 |
+
"41": "base(double)",
|
57 |
+
"42": "base(unsigned char)**",
|
58 |
+
"43": "union",
|
59 |
+
"44": "base(short int)",
|
60 |
+
"45": "base(long long unsigned int)",
|
61 |
+
"46": "subroutine**",
|
62 |
+
"47": "array**",
|
63 |
+
"48": "base(signed char)",
|
64 |
+
"49": "base(float)"
|
65 |
+
},
|
66 |
+
"initializer_range": 0.02,
|
67 |
+
"intermediate_size": 3072,
|
68 |
+
"label2id": {
|
69 |
+
"array": 40,
|
70 |
+
"array*": 20,
|
71 |
+
"array**": 47,
|
72 |
+
"base(_Bool)": 4,
|
73 |
+
"base(_Bool)*": 27,
|
74 |
+
"base(char)": 12,
|
75 |
+
"base(char)*": 3,
|
76 |
+
"base(char)**": 2,
|
77 |
+
"base(char)***": 28,
|
78 |
+
"base(double)": 41,
|
79 |
+
"base(double)*": 23,
|
80 |
+
"base(float)": 49,
|
81 |
+
"base(float)*": 35,
|
82 |
+
"base(int)": 1,
|
83 |
+
"base(int)*": 19,
|
84 |
+
"base(long double)": 30,
|
85 |
+
"base(long double)*": 34,
|
86 |
+
"base(long int)": 14,
|
87 |
+
"base(long int)*": 18,
|
88 |
+
"base(long long int)": 39,
|
89 |
+
"base(long long unsigned int)": 45,
|
90 |
+
"base(long long unsigned int)*": 36,
|
91 |
+
"base(long unsigned int)": 6,
|
92 |
+
"base(long unsigned int)*": 22,
|
93 |
+
"base(long unsigned int)**": 29,
|
94 |
+
"base(short int)": 44,
|
95 |
+
"base(short int)*": 15,
|
96 |
+
"base(short unsigned int)": 25,
|
97 |
+
"base(short unsigned int)*": 37,
|
98 |
+
"base(signed char)": 48,
|
99 |
+
"base(signed char)*": 38,
|
100 |
+
"base(unsigned char)": 11,
|
101 |
+
"base(unsigned char)*": 9,
|
102 |
+
"base(unsigned char)**": 42,
|
103 |
+
"base(unsigned int)": 5,
|
104 |
+
"base(unsigned int)*": 13,
|
105 |
+
"base(unsigned int)**": 33,
|
106 |
+
"enum": 10,
|
107 |
+
"enum*": 32,
|
108 |
+
"noacc": 0,
|
109 |
+
"struct": 26,
|
110 |
+
"struct*": 7,
|
111 |
+
"struct**": 21,
|
112 |
+
"struct***": 31,
|
113 |
+
"subroutine*": 17,
|
114 |
+
"subroutine**": 46,
|
115 |
+
"union": 43,
|
116 |
+
"union*": 16,
|
117 |
+
"void*": 8,
|
118 |
+
"void**": 24
|
119 |
+
},
|
120 |
+
"layer_norm_eps": 1e-12,
|
121 |
+
"max_position_embeddings": 600,
|
122 |
+
"max_relative_position_embeddings": 8,
|
123 |
+
"model_type": "codeart",
|
124 |
+
"num_attention_heads": 12,
|
125 |
+
"num_hidden_layers": 12,
|
126 |
+
"pad_token_id": 3,
|
127 |
+
"position_embedding_type": "mixed",
|
128 |
+
"torch_dtype": "float32",
|
129 |
+
"transformers_version": "4.30.2",
|
130 |
+
"type_vocab_size": 2,
|
131 |
+
"use_cache": true,
|
132 |
+
"vocab_size": 30523
|
133 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7715f44d6842bb626fdce650e14755ec8e65fedb1313d43140f8c4cdddfc484a
|
3 |
+
size 436071129
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"model_max_length": 512,
|
4 |
+
"tokenizer_class": "CodeArtTokenizer"
|
5 |
+
}
|