vijaym commited on
Commit
c96794f
·
verified ·
1 Parent(s): 043277d

Initial release: 107-language classifier

Browse files
.gitattributes CHANGED
@@ -1,35 +1,3 @@
1
- *.7z filter=lfs diff=lfs merge=lfs -text
2
- *.arrow filter=lfs diff=lfs merge=lfs -text
3
- *.bin filter=lfs diff=lfs merge=lfs -text
4
- *.bz2 filter=lfs diff=lfs merge=lfs -text
5
- *.ckpt filter=lfs diff=lfs merge=lfs -text
6
- *.ftz filter=lfs diff=lfs merge=lfs -text
7
- *.gz filter=lfs diff=lfs merge=lfs -text
8
- *.h5 filter=lfs diff=lfs merge=lfs -text
9
- *.joblib filter=lfs diff=lfs merge=lfs -text
10
- *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
- *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
- *.model filter=lfs diff=lfs merge=lfs -text
13
- *.msgpack filter=lfs diff=lfs merge=lfs -text
14
- *.npy filter=lfs diff=lfs merge=lfs -text
15
- *.npz filter=lfs diff=lfs merge=lfs -text
16
- *.onnx filter=lfs diff=lfs merge=lfs -text
17
- *.ot filter=lfs diff=lfs merge=lfs -text
18
- *.parquet filter=lfs diff=lfs merge=lfs -text
19
- *.pb filter=lfs diff=lfs merge=lfs -text
20
- *.pickle filter=lfs diff=lfs merge=lfs -text
21
- *.pkl filter=lfs diff=lfs merge=lfs -text
22
- *.pt filter=lfs diff=lfs merge=lfs -text
23
- *.pth filter=lfs diff=lfs merge=lfs -text
24
- *.rar filter=lfs diff=lfs merge=lfs -text
25
  *.safetensors filter=lfs diff=lfs merge=lfs -text
26
- saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
- *.tar.* filter=lfs diff=lfs merge=lfs -text
28
- *.tar filter=lfs diff=lfs merge=lfs -text
29
- *.tflite filter=lfs diff=lfs merge=lfs -text
30
- *.tgz filter=lfs diff=lfs merge=lfs -text
31
- *.wasm filter=lfs diff=lfs merge=lfs -text
32
- *.xz filter=lfs diff=lfs merge=lfs -text
33
- *.zip filter=lfs diff=lfs merge=lfs -text
34
- *.zst filter=lfs diff=lfs merge=lfs -text
35
- *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  *.safetensors filter=lfs diff=lfs merge=lfs -text
2
+ *.bin filter=lfs diff=lfs merge=lfs -text
3
+ onnx/model.onnx filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
README.md ADDED
@@ -0,0 +1,169 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: transformers
4
+ pipeline_tag: text-classification
5
+ tags:
6
+ - text-classification
7
+ - code
8
+ - programming-language-identification
9
+ - language-detection
10
+ - modernbert
11
+ base_model: answerdotai/ModernBERT-base
12
+ datasets:
13
+ - cakiki/rosetta-code
14
+ - bigcode/the-stack
15
+ metrics:
16
+ - accuracy
17
+ - f1
18
+ ---
19
+
20
+ # Programming Language Identification (100+ languages)
21
+
22
+ A ModernBERT classifier that identifies the programming language of a code
23
+ snippet across **107 languages**.
24
+
25
+ ## Inference
26
+
27
+ Weights are published in **bfloat16** (`model.safetensors`, ~286 MB). The
28
+ ONNX export is **float16** (`onnx/model.onnx`, ~286 MB).
29
+
30
+ ### Single snippet (PyTorch, bf16)
31
+
32
+ ```python
33
+ import torch
34
+ from transformers import AutoModelForSequenceClassification, AutoTokenizer
35
+
36
+ model_id = "programming-language-identification-100plus" # or your HF repo id
37
+ tokenizer = AutoTokenizer.from_pretrained(model_id)
38
+ model = AutoModelForSequenceClassification.from_pretrained(
39
+ model_id,
40
+ attn_implementation="eager",
41
+ torch_dtype=torch.bfloat16,
42
+ ).eval()
43
+
44
+ code = "def greet(name: str) -> None:\n print(f'hello, {name}')"
45
+ inputs = tokenizer(code, return_tensors="pt", truncation=True, max_length=512)
46
+ with torch.no_grad():
47
+ logits = model(**inputs).logits
48
+ print(model.config.id2label[int(logits.argmax(-1))]) # -> "Python"
49
+ ```
50
+
51
+ Passing `torch_dtype=torch.bfloat16` keeps the weights in bf16 for inference.
52
+ Omit it to run in fp32 (HF will upcast). `attn_implementation="eager"` is
53
+ recommended — the SDPA path has produced NaNs on some ModernBERT builds.
54
+
55
+ ### Batch
56
+
57
+ ```python
58
+ snippets = [py_code, rust_code, go_code] # list of strings
59
+ inputs = tokenizer(
60
+ snippets, return_tensors="pt", padding=True, truncation=True, max_length=512
61
+ )
62
+ with torch.no_grad():
63
+ logits = model(**inputs).logits
64
+ for i, pred in enumerate(logits.argmax(-1).tolist()):
65
+ print(snippets[i][:40].splitlines()[0], "→", model.config.id2label[pred])
66
+ ```
67
+
68
+ ### ONNX Runtime (fp16)
69
+
70
+ An ONNX export in fp16 lives in `onnx/` (~286 MB). Use it for CPU or GPU
71
+ inference without pulling PyTorch — handy for non-Python consumers and edge
72
+ deployments.
73
+
74
+ ```python
75
+ from optimum.onnxruntime import ORTModelForSequenceClassification
76
+ from transformers import AutoTokenizer
77
+
78
+ model_id = "programming-language-identification-100plus" # or your HF repo id
79
+ tokenizer = AutoTokenizer.from_pretrained(model_id)
80
+ ort_model = ORTModelForSequenceClassification.from_pretrained(
81
+ model_id, subfolder="onnx"
82
+ )
83
+
84
+ inputs = tokenizer(code, return_tensors="pt", truncation=True, max_length=512)
85
+ logits = ort_model(**inputs).logits
86
+ print(ort_model.config.id2label[int(logits.argmax(-1))])
87
+ ```
88
+
89
+ Argmax predictions match the PyTorch model (verified on a 500-row validation
90
+ sample — fp16 ONNX accuracy 0.940 vs bf16 PyTorch 0.940).
91
+
92
+ ### Top-k with confidence
93
+
94
+ ```python
95
+ probs = logits.softmax(-1)
96
+ top_probs, top_ids = probs.topk(3, dim=-1)
97
+ for prob, label_id in zip(top_probs[0].tolist(), top_ids[0].tolist()):
98
+ print(f"{model.config.id2label[label_id]:30s} {prob:.3f}")
99
+ ```
100
+
101
+ Tip: for the first 512 characters, trim the snippet before tokenizing — the
102
+ model was trained and evaluated with the `head` strategy at inference time.
103
+
104
+ See [`notebooks/inference_examples.ipynb`](../../../workspace/projects/accuknox/guardrail/code-language-id/notebooks/inference_examples.ipynb)
105
+ for a runnable walkthrough.
106
+
107
+ ## Evaluation
108
+
109
+ Held-out validation split (9,495 rows, 107 labels):
110
+
111
+ | metric | value |
112
+ |---|---|
113
+ | macro F1 | **0.9206** |
114
+ | accuracy | 0.9306 |
115
+
116
+ Head-to-head vs `philomath-1209/programming-language-identification` on the 26
117
+ labels both models support (3,057 test rows):
118
+
119
+ | model | accuracy | macro F1 |
120
+ |---|---|---|
121
+ | **this model** | **0.9444** | **0.9636** |
122
+ | philomath-1209 | 0.8449 | 0.8445 |
123
+
124
+ Wins on every shared label. Largest gaps: ARM Assembly +0.354, Erlang +0.270,
125
+ COBOL +0.216, Pascal +0.206, Fortran +0.193, Mathematica/Wolfram +0.173.
126
+
127
+ ## Supported languages (107)
128
+
129
+ ABAP, APL, ARM Assembly, ATS, Ada, ActionScript, AppleScript, AutoHotkey,
130
+ AutoIt, Awk, BASIC, BQN, Batchfile, Befunge, C, C#, C++, COBOL, Ceylon,
131
+ Clojure, CoffeeScript, ColdFusion, Common Lisp, Component Pascal, Crystal, D,
132
+ Dart, E, Eiffel, Elixir, Emacs Lisp, Erlang, Euphoria, F#, Factor, Fantom,
133
+ Forth, Fortran, FreeBASIC, GAP, Go, Groovy, Haskell, Haxe, IDL, Io, J, Java,
134
+ JavaScript, Julia, Kotlin, LabVIEW, LFE, Lasso, Logtalk, Lua, M, M4, MATLAB,
135
+ MAXScript, Mathematica/Wolfram Language, Mercury, Modula-2, Modula-3, Nemerle,
136
+ NewLisp, Nim, OCaml, Objective-C, Oz, PHP, Pascal, Perl, Pike, PicoLisp,
137
+ PowerShell, Processing, Prolog, PureBasic, Python, QuickBASIC, R, REXX, Raku,
138
+ Racket, Rebol, Red, Ring, Ruby, Rust, SAS, Scala, Scheme, Scilab, Smalltalk,
139
+ Standard ML, Stata, Swift, Tcl, V, VBA, VBScript, Vala, Visual Basic .NET,
140
+ Wren, Zig, jq
141
+
142
+ ## Training data
143
+
144
+ 91,209 code samples across 107 languages, drawn from Rosetta Code
145
+ (`cakiki/rosetta-code`) and The Stack v1 (`bigcode/the-stack`). Labels were
146
+ independently verified by an LLM judge, and a small set of high-confidence
147
+ mislabels between mainstream languages was removed.
148
+
149
+ Splits are grouped by task to prevent task-level leakage:
150
+ 72,549 / 9,495 / 8,880 rows (train / val / test).
151
+
152
+ ## Training
153
+
154
+ - Base: `answerdotai/ModernBERT-base`
155
+ - 10 epochs, bf16, AdamW (lr 2e-5, weight decay 0.01)
156
+ - Linear schedule, 6% warmup
157
+ - Attention: eager
158
+ - Augmentation: random-window over the source code per training step
159
+ (window length ∈ [64, 512] chars, random offset). Evaluation takes the
160
+ first 512 characters.
161
+
162
+ ## Limitations
163
+
164
+ - Input is truncated to 512 characters. Very short snippets (<60 chars) are
165
+ inherently ambiguous.
166
+ - Rare languages (PicoLisp, LabVIEW, Lasso, Wren, Ring, Fantom, Pike, etc.)
167
+ have lower per-label F1 because training data for them is scarce.
168
+ - The classifier is purely content-based — it does not read file extensions
169
+ or shebang lines. In production, combine it with extension heuristics.
config.json ADDED
@@ -0,0 +1,266 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertForSequenceClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 50281,
8
+ "classifier_activation": "gelu",
9
+ "classifier_bias": false,
10
+ "classifier_dropout": 0.0,
11
+ "classifier_pooling": "mean",
12
+ "cls_token_id": 50281,
13
+ "decoder_bias": true,
14
+ "deterministic_flash_attn": false,
15
+ "dtype": "float32",
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 50282,
18
+ "global_attn_every_n_layers": 3,
19
+ "global_rope_theta": 160000.0,
20
+ "gradient_checkpointing": false,
21
+ "hidden_activation": "gelu",
22
+ "hidden_size": 768,
23
+ "id2label": {
24
+ "0": "Julia",
25
+ "1": "Go",
26
+ "2": "Raku",
27
+ "3": "Pascal",
28
+ "4": "Perl",
29
+ "5": "Python",
30
+ "6": "Nim",
31
+ "7": "J",
32
+ "8": "C",
33
+ "9": "Haskell",
34
+ "10": "Mathematica/Wolfram Language",
35
+ "11": "Kotlin",
36
+ "12": "Java",
37
+ "13": "Ruby",
38
+ "14": "Racket",
39
+ "15": "C++",
40
+ "16": "Tcl",
41
+ "17": "C#",
42
+ "18": "Scala",
43
+ "19": "Ada",
44
+ "20": "Factor",
45
+ "21": "Rust",
46
+ "22": "Lua",
47
+ "23": "D",
48
+ "24": "Common Lisp",
49
+ "25": "AutoHotkey",
50
+ "26": "JavaScript",
51
+ "27": "F#",
52
+ "28": "Wren",
53
+ "29": "Clojure",
54
+ "30": "Fortran",
55
+ "31": "PureBasic",
56
+ "32": "OCaml",
57
+ "33": "Awk",
58
+ "34": "R",
59
+ "35": "Swift",
60
+ "36": "Forth",
61
+ "37": "Elixir",
62
+ "38": "Erlang",
63
+ "39": "PowerShell",
64
+ "40": "Groovy",
65
+ "41": "REXX",
66
+ "42": "Visual Basic .NET",
67
+ "43": "PHP",
68
+ "44": "Prolog",
69
+ "45": "Scheme",
70
+ "46": "AppleScript",
71
+ "47": "COBOL",
72
+ "48": "FreeBASIC",
73
+ "49": "Smalltalk",
74
+ "50": "PicoLisp",
75
+ "51": "MATLAB",
76
+ "52": "Oz",
77
+ "53": "Standard ML",
78
+ "54": "Lasso",
79
+ "55": "Crystal",
80
+ "56": "APL",
81
+ "57": "Stata",
82
+ "58": "CoffeeScript",
83
+ "59": "Batchfile",
84
+ "60": "jq",
85
+ "61": "GAP",
86
+ "62": "Red",
87
+ "63": "Emacs Lisp",
88
+ "64": "Eiffel",
89
+ "65": "Fantom",
90
+ "66": "Ring",
91
+ "67": "Pike",
92
+ "68": "Rebol",
93
+ "69": "ActionScript",
94
+ "70": "MAXScript",
95
+ "71": "Vala",
96
+ "72": "Dart",
97
+ "73": "Processing",
98
+ "74": "Ceylon",
99
+ "75": "AutoIt",
100
+ "76": "Io",
101
+ "77": "M4",
102
+ "78": "Zig",
103
+ "79": "LFE",
104
+ "80": "ATS",
105
+ "81": "Logtalk",
106
+ "82": "ABAP",
107
+ "83": "Scilab",
108
+ "84": "IDL",
109
+ "85": "LabVIEW",
110
+ "86": "ColdFusion",
111
+ "87": "SAS",
112
+ "88": "Haxe",
113
+ "89": "VBA",
114
+ "90": "BASIC",
115
+ "91": "V",
116
+ "92": "VBScript",
117
+ "93": "E",
118
+ "94": "Euphoria",
119
+ "95": "ARM Assembly",
120
+ "96": "Component Pascal",
121
+ "97": "M",
122
+ "98": "Modula-2",
123
+ "99": "BQN",
124
+ "100": "Befunge",
125
+ "101": "Objective-C",
126
+ "102": "NewLisp",
127
+ "103": "Nemerle",
128
+ "104": "Modula-3",
129
+ "105": "Mercury",
130
+ "106": "QuickBASIC"
131
+ },
132
+ "initializer_cutoff_factor": 2.0,
133
+ "initializer_range": 0.02,
134
+ "intermediate_size": 1152,
135
+ "label2id": {
136
+ "ABAP": 82,
137
+ "APL": 56,
138
+ "ARM Assembly": 95,
139
+ "ATS": 80,
140
+ "ActionScript": 69,
141
+ "Ada": 19,
142
+ "AppleScript": 46,
143
+ "AutoHotkey": 25,
144
+ "AutoIt": 75,
145
+ "Awk": 33,
146
+ "BASIC": 90,
147
+ "BQN": 99,
148
+ "Batchfile": 59,
149
+ "Befunge": 100,
150
+ "C": 8,
151
+ "C#": 17,
152
+ "C++": 15,
153
+ "COBOL": 47,
154
+ "Ceylon": 74,
155
+ "Clojure": 29,
156
+ "CoffeeScript": 58,
157
+ "ColdFusion": 86,
158
+ "Common Lisp": 24,
159
+ "Component Pascal": 96,
160
+ "Crystal": 55,
161
+ "D": 23,
162
+ "Dart": 72,
163
+ "E": 93,
164
+ "Eiffel": 64,
165
+ "Elixir": 37,
166
+ "Emacs Lisp": 63,
167
+ "Erlang": 38,
168
+ "Euphoria": 94,
169
+ "F#": 27,
170
+ "Factor": 20,
171
+ "Fantom": 65,
172
+ "Forth": 36,
173
+ "Fortran": 30,
174
+ "FreeBASIC": 48,
175
+ "GAP": 61,
176
+ "Go": 1,
177
+ "Groovy": 40,
178
+ "Haskell": 9,
179
+ "Haxe": 88,
180
+ "IDL": 84,
181
+ "Io": 76,
182
+ "J": 7,
183
+ "Java": 12,
184
+ "JavaScript": 26,
185
+ "Julia": 0,
186
+ "Kotlin": 11,
187
+ "LFE": 79,
188
+ "LabVIEW": 85,
189
+ "Lasso": 54,
190
+ "Logtalk": 81,
191
+ "Lua": 22,
192
+ "M": 97,
193
+ "M4": 77,
194
+ "MATLAB": 51,
195
+ "MAXScript": 70,
196
+ "Mathematica/Wolfram Language": 10,
197
+ "Mercury": 105,
198
+ "Modula-2": 98,
199
+ "Modula-3": 104,
200
+ "Nemerle": 103,
201
+ "NewLisp": 102,
202
+ "Nim": 6,
203
+ "OCaml": 32,
204
+ "Objective-C": 101,
205
+ "Oz": 52,
206
+ "PHP": 43,
207
+ "Pascal": 3,
208
+ "Perl": 4,
209
+ "PicoLisp": 50,
210
+ "Pike": 67,
211
+ "PowerShell": 39,
212
+ "Processing": 73,
213
+ "Prolog": 44,
214
+ "PureBasic": 31,
215
+ "Python": 5,
216
+ "QuickBASIC": 106,
217
+ "R": 34,
218
+ "REXX": 41,
219
+ "Racket": 14,
220
+ "Raku": 2,
221
+ "Rebol": 68,
222
+ "Red": 62,
223
+ "Ring": 66,
224
+ "Ruby": 13,
225
+ "Rust": 21,
226
+ "SAS": 87,
227
+ "Scala": 18,
228
+ "Scheme": 45,
229
+ "Scilab": 83,
230
+ "Smalltalk": 49,
231
+ "Standard ML": 53,
232
+ "Stata": 57,
233
+ "Swift": 35,
234
+ "Tcl": 16,
235
+ "V": 91,
236
+ "VBA": 89,
237
+ "VBScript": 92,
238
+ "Vala": 71,
239
+ "Visual Basic .NET": 42,
240
+ "Wren": 28,
241
+ "Zig": 78,
242
+ "jq": 60
243
+ },
244
+ "layer_norm_eps": 1e-05,
245
+ "local_attention": 128,
246
+ "local_rope_theta": 10000.0,
247
+ "max_position_embeddings": 8192,
248
+ "mlp_bias": false,
249
+ "mlp_dropout": 0.0,
250
+ "model_type": "modernbert",
251
+ "norm_bias": false,
252
+ "norm_eps": 1e-05,
253
+ "num_attention_heads": 12,
254
+ "num_hidden_layers": 22,
255
+ "pad_token_id": 50283,
256
+ "position_embedding_type": "absolute",
257
+ "problem_type": "single_label_classification",
258
+ "repad_logits_with_grad": false,
259
+ "sep_token_id": 50282,
260
+ "sparse_pred_ignore_index": -100,
261
+ "sparse_prediction": false,
262
+ "transformers_version": "4.57.6",
263
+ "vocab_size": 50368,
264
+ "reference_compile": false,
265
+ "torch_dtype": "bfloat16"
266
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52b6b9deceb722e8147f9115c0bf7ab8d7fa2a7a64ce6b63444bb82f8788e09d
3
+ size 299388590
onnx/config.json ADDED
@@ -0,0 +1,264 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertForSequenceClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 50281,
8
+ "classifier_activation": "gelu",
9
+ "classifier_bias": false,
10
+ "classifier_dropout": 0.0,
11
+ "classifier_pooling": "mean",
12
+ "cls_token_id": 50281,
13
+ "decoder_bias": true,
14
+ "deterministic_flash_attn": false,
15
+ "dtype": "float16",
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 50282,
18
+ "global_attn_every_n_layers": 3,
19
+ "global_rope_theta": 160000.0,
20
+ "gradient_checkpointing": false,
21
+ "hidden_activation": "gelu",
22
+ "hidden_size": 768,
23
+ "id2label": {
24
+ "0": "Julia",
25
+ "1": "Go",
26
+ "2": "Raku",
27
+ "3": "Pascal",
28
+ "4": "Perl",
29
+ "5": "Python",
30
+ "6": "Nim",
31
+ "7": "J",
32
+ "8": "C",
33
+ "9": "Haskell",
34
+ "10": "Mathematica/Wolfram Language",
35
+ "11": "Kotlin",
36
+ "12": "Java",
37
+ "13": "Ruby",
38
+ "14": "Racket",
39
+ "15": "C++",
40
+ "16": "Tcl",
41
+ "17": "C#",
42
+ "18": "Scala",
43
+ "19": "Ada",
44
+ "20": "Factor",
45
+ "21": "Rust",
46
+ "22": "Lua",
47
+ "23": "D",
48
+ "24": "Common Lisp",
49
+ "25": "AutoHotkey",
50
+ "26": "JavaScript",
51
+ "27": "F#",
52
+ "28": "Wren",
53
+ "29": "Clojure",
54
+ "30": "Fortran",
55
+ "31": "PureBasic",
56
+ "32": "OCaml",
57
+ "33": "Awk",
58
+ "34": "R",
59
+ "35": "Swift",
60
+ "36": "Forth",
61
+ "37": "Elixir",
62
+ "38": "Erlang",
63
+ "39": "PowerShell",
64
+ "40": "Groovy",
65
+ "41": "REXX",
66
+ "42": "Visual Basic .NET",
67
+ "43": "PHP",
68
+ "44": "Prolog",
69
+ "45": "Scheme",
70
+ "46": "AppleScript",
71
+ "47": "COBOL",
72
+ "48": "FreeBASIC",
73
+ "49": "Smalltalk",
74
+ "50": "PicoLisp",
75
+ "51": "MATLAB",
76
+ "52": "Oz",
77
+ "53": "Standard ML",
78
+ "54": "Lasso",
79
+ "55": "Crystal",
80
+ "56": "APL",
81
+ "57": "Stata",
82
+ "58": "CoffeeScript",
83
+ "59": "Batchfile",
84
+ "60": "jq",
85
+ "61": "GAP",
86
+ "62": "Red",
87
+ "63": "Emacs Lisp",
88
+ "64": "Eiffel",
89
+ "65": "Fantom",
90
+ "66": "Ring",
91
+ "67": "Pike",
92
+ "68": "Rebol",
93
+ "69": "ActionScript",
94
+ "70": "MAXScript",
95
+ "71": "Vala",
96
+ "72": "Dart",
97
+ "73": "Processing",
98
+ "74": "Ceylon",
99
+ "75": "AutoIt",
100
+ "76": "Io",
101
+ "77": "M4",
102
+ "78": "Zig",
103
+ "79": "LFE",
104
+ "80": "ATS",
105
+ "81": "Logtalk",
106
+ "82": "ABAP",
107
+ "83": "Scilab",
108
+ "84": "IDL",
109
+ "85": "LabVIEW",
110
+ "86": "ColdFusion",
111
+ "87": "SAS",
112
+ "88": "Haxe",
113
+ "89": "VBA",
114
+ "90": "BASIC",
115
+ "91": "V",
116
+ "92": "VBScript",
117
+ "93": "E",
118
+ "94": "Euphoria",
119
+ "95": "ARM Assembly",
120
+ "96": "Component Pascal",
121
+ "97": "M",
122
+ "98": "Modula-2",
123
+ "99": "BQN",
124
+ "100": "Befunge",
125
+ "101": "Objective-C",
126
+ "102": "NewLisp",
127
+ "103": "Nemerle",
128
+ "104": "Modula-3",
129
+ "105": "Mercury",
130
+ "106": "QuickBASIC"
131
+ },
132
+ "initializer_cutoff_factor": 2.0,
133
+ "initializer_range": 0.02,
134
+ "intermediate_size": 1152,
135
+ "label2id": {
136
+ "ABAP": 82,
137
+ "APL": 56,
138
+ "ARM Assembly": 95,
139
+ "ATS": 80,
140
+ "ActionScript": 69,
141
+ "Ada": 19,
142
+ "AppleScript": 46,
143
+ "AutoHotkey": 25,
144
+ "AutoIt": 75,
145
+ "Awk": 33,
146
+ "BASIC": 90,
147
+ "BQN": 99,
148
+ "Batchfile": 59,
149
+ "Befunge": 100,
150
+ "C": 8,
151
+ "C#": 17,
152
+ "C++": 15,
153
+ "COBOL": 47,
154
+ "Ceylon": 74,
155
+ "Clojure": 29,
156
+ "CoffeeScript": 58,
157
+ "ColdFusion": 86,
158
+ "Common Lisp": 24,
159
+ "Component Pascal": 96,
160
+ "Crystal": 55,
161
+ "D": 23,
162
+ "Dart": 72,
163
+ "E": 93,
164
+ "Eiffel": 64,
165
+ "Elixir": 37,
166
+ "Emacs Lisp": 63,
167
+ "Erlang": 38,
168
+ "Euphoria": 94,
169
+ "F#": 27,
170
+ "Factor": 20,
171
+ "Fantom": 65,
172
+ "Forth": 36,
173
+ "Fortran": 30,
174
+ "FreeBASIC": 48,
175
+ "GAP": 61,
176
+ "Go": 1,
177
+ "Groovy": 40,
178
+ "Haskell": 9,
179
+ "Haxe": 88,
180
+ "IDL": 84,
181
+ "Io": 76,
182
+ "J": 7,
183
+ "Java": 12,
184
+ "JavaScript": 26,
185
+ "Julia": 0,
186
+ "Kotlin": 11,
187
+ "LFE": 79,
188
+ "LabVIEW": 85,
189
+ "Lasso": 54,
190
+ "Logtalk": 81,
191
+ "Lua": 22,
192
+ "M": 97,
193
+ "M4": 77,
194
+ "MATLAB": 51,
195
+ "MAXScript": 70,
196
+ "Mathematica/Wolfram Language": 10,
197
+ "Mercury": 105,
198
+ "Modula-2": 98,
199
+ "Modula-3": 104,
200
+ "Nemerle": 103,
201
+ "NewLisp": 102,
202
+ "Nim": 6,
203
+ "OCaml": 32,
204
+ "Objective-C": 101,
205
+ "Oz": 52,
206
+ "PHP": 43,
207
+ "Pascal": 3,
208
+ "Perl": 4,
209
+ "PicoLisp": 50,
210
+ "Pike": 67,
211
+ "PowerShell": 39,
212
+ "Processing": 73,
213
+ "Prolog": 44,
214
+ "PureBasic": 31,
215
+ "Python": 5,
216
+ "QuickBASIC": 106,
217
+ "R": 34,
218
+ "REXX": 41,
219
+ "Racket": 14,
220
+ "Raku": 2,
221
+ "Rebol": 68,
222
+ "Red": 62,
223
+ "Ring": 66,
224
+ "Ruby": 13,
225
+ "Rust": 21,
226
+ "SAS": 87,
227
+ "Scala": 18,
228
+ "Scheme": 45,
229
+ "Scilab": 83,
230
+ "Smalltalk": 49,
231
+ "Standard ML": 53,
232
+ "Stata": 57,
233
+ "Swift": 35,
234
+ "Tcl": 16,
235
+ "V": 91,
236
+ "VBA": 89,
237
+ "VBScript": 92,
238
+ "Vala": 71,
239
+ "Visual Basic .NET": 42,
240
+ "Wren": 28,
241
+ "Zig": 78,
242
+ "jq": 60
243
+ },
244
+ "layer_norm_eps": 1e-05,
245
+ "local_attention": 128,
246
+ "local_rope_theta": 10000.0,
247
+ "max_position_embeddings": 8192,
248
+ "mlp_bias": false,
249
+ "mlp_dropout": 0.0,
250
+ "model_type": "modernbert",
251
+ "norm_bias": false,
252
+ "norm_eps": 1e-05,
253
+ "num_attention_heads": 12,
254
+ "num_hidden_layers": 22,
255
+ "pad_token_id": 50283,
256
+ "position_embedding_type": "absolute",
257
+ "problem_type": "single_label_classification",
258
+ "repad_logits_with_grad": false,
259
+ "sep_token_id": 50282,
260
+ "sparse_pred_ignore_index": -100,
261
+ "sparse_prediction": false,
262
+ "transformers_version": "4.57.6",
263
+ "vocab_size": 50368
264
+ }
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11574821c81bab1bf8677e06f2fd9036fbf19f3e714d7e9a2d1bb3ce61e9ea91
3
+ size 299880933
onnx/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
onnx/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
onnx/tokenizer_config.json ADDED
@@ -0,0 +1,952 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "|||IP_ADDRESS|||",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "1": {
12
+ "content": "<|padding|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "50254": {
20
+ "content": " ",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "50255": {
28
+ "content": " ",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "50256": {
36
+ "content": " ",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "50257": {
44
+ "content": " ",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "50258": {
52
+ "content": " ",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "50259": {
60
+ "content": " ",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "50260": {
68
+ "content": " ",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "50261": {
76
+ "content": " ",
77
+ "lstrip": false,
78
+ "normalized": true,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "50262": {
84
+ "content": " ",
85
+ "lstrip": false,
86
+ "normalized": true,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "50263": {
92
+ "content": " ",
93
+ "lstrip": false,
94
+ "normalized": true,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "50264": {
100
+ "content": " ",
101
+ "lstrip": false,
102
+ "normalized": true,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "50265": {
108
+ "content": " ",
109
+ "lstrip": false,
110
+ "normalized": true,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "50266": {
116
+ "content": " ",
117
+ "lstrip": false,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "50267": {
124
+ "content": " ",
125
+ "lstrip": false,
126
+ "normalized": true,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "50268": {
132
+ "content": " ",
133
+ "lstrip": false,
134
+ "normalized": true,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "50269": {
140
+ "content": " ",
141
+ "lstrip": false,
142
+ "normalized": true,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "50270": {
148
+ "content": " ",
149
+ "lstrip": false,
150
+ "normalized": true,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "50271": {
156
+ "content": " ",
157
+ "lstrip": false,
158
+ "normalized": true,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "50272": {
164
+ "content": " ",
165
+ "lstrip": false,
166
+ "normalized": true,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "50273": {
172
+ "content": " ",
173
+ "lstrip": false,
174
+ "normalized": true,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "50274": {
180
+ "content": " ",
181
+ "lstrip": false,
182
+ "normalized": true,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "50275": {
188
+ "content": " ",
189
+ "lstrip": false,
190
+ "normalized": true,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "50276": {
196
+ "content": " ",
197
+ "lstrip": false,
198
+ "normalized": true,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "50277": {
204
+ "content": "|||EMAIL_ADDRESS|||",
205
+ "lstrip": false,
206
+ "normalized": true,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "50278": {
212
+ "content": "|||PHONE_NUMBER|||",
213
+ "lstrip": false,
214
+ "normalized": true,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "50279": {
220
+ "content": "<|endoftext|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "50280": {
228
+ "content": "[UNK]",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "50281": {
236
+ "content": "[CLS]",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "50282": {
244
+ "content": "[SEP]",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "50283": {
252
+ "content": "[PAD]",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "50284": {
260
+ "content": "[MASK]",
261
+ "lstrip": true,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "50285": {
268
+ "content": "[unused0]",
269
+ "lstrip": false,
270
+ "normalized": true,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "50286": {
276
+ "content": "[unused1]",
277
+ "lstrip": false,
278
+ "normalized": true,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "50287": {
284
+ "content": "[unused2]",
285
+ "lstrip": false,
286
+ "normalized": true,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "50288": {
292
+ "content": "[unused3]",
293
+ "lstrip": false,
294
+ "normalized": true,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": false
298
+ },
299
+ "50289": {
300
+ "content": "[unused4]",
301
+ "lstrip": false,
302
+ "normalized": true,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": false
306
+ },
307
+ "50290": {
308
+ "content": "[unused5]",
309
+ "lstrip": false,
310
+ "normalized": true,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": false
314
+ },
315
+ "50291": {
316
+ "content": "[unused6]",
317
+ "lstrip": false,
318
+ "normalized": true,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": false
322
+ },
323
+ "50292": {
324
+ "content": "[unused7]",
325
+ "lstrip": false,
326
+ "normalized": true,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": false
330
+ },
331
+ "50293": {
332
+ "content": "[unused8]",
333
+ "lstrip": false,
334
+ "normalized": true,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": false
338
+ },
339
+ "50294": {
340
+ "content": "[unused9]",
341
+ "lstrip": false,
342
+ "normalized": true,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": false
346
+ },
347
+ "50295": {
348
+ "content": "[unused10]",
349
+ "lstrip": false,
350
+ "normalized": true,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": false
354
+ },
355
+ "50296": {
356
+ "content": "[unused11]",
357
+ "lstrip": false,
358
+ "normalized": true,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": false
362
+ },
363
+ "50297": {
364
+ "content": "[unused12]",
365
+ "lstrip": false,
366
+ "normalized": true,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": false
370
+ },
371
+ "50298": {
372
+ "content": "[unused13]",
373
+ "lstrip": false,
374
+ "normalized": true,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": false
378
+ },
379
+ "50299": {
380
+ "content": "[unused14]",
381
+ "lstrip": false,
382
+ "normalized": true,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": false
386
+ },
387
+ "50300": {
388
+ "content": "[unused15]",
389
+ "lstrip": false,
390
+ "normalized": true,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": false
394
+ },
395
+ "50301": {
396
+ "content": "[unused16]",
397
+ "lstrip": false,
398
+ "normalized": true,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": false
402
+ },
403
+ "50302": {
404
+ "content": "[unused17]",
405
+ "lstrip": false,
406
+ "normalized": true,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": false
410
+ },
411
+ "50303": {
412
+ "content": "[unused18]",
413
+ "lstrip": false,
414
+ "normalized": true,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": false
418
+ },
419
+ "50304": {
420
+ "content": "[unused19]",
421
+ "lstrip": false,
422
+ "normalized": true,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": false
426
+ },
427
+ "50305": {
428
+ "content": "[unused20]",
429
+ "lstrip": false,
430
+ "normalized": true,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": false
434
+ },
435
+ "50306": {
436
+ "content": "[unused21]",
437
+ "lstrip": false,
438
+ "normalized": true,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": false
442
+ },
443
+ "50307": {
444
+ "content": "[unused22]",
445
+ "lstrip": false,
446
+ "normalized": true,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": false
450
+ },
451
+ "50308": {
452
+ "content": "[unused23]",
453
+ "lstrip": false,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": false
458
+ },
459
+ "50309": {
460
+ "content": "[unused24]",
461
+ "lstrip": false,
462
+ "normalized": true,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": false
466
+ },
467
+ "50310": {
468
+ "content": "[unused25]",
469
+ "lstrip": false,
470
+ "normalized": true,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": false
474
+ },
475
+ "50311": {
476
+ "content": "[unused26]",
477
+ "lstrip": false,
478
+ "normalized": true,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": false
482
+ },
483
+ "50312": {
484
+ "content": "[unused27]",
485
+ "lstrip": false,
486
+ "normalized": true,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": false
490
+ },
491
+ "50313": {
492
+ "content": "[unused28]",
493
+ "lstrip": false,
494
+ "normalized": true,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": false
498
+ },
499
+ "50314": {
500
+ "content": "[unused29]",
501
+ "lstrip": false,
502
+ "normalized": true,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": false
506
+ },
507
+ "50315": {
508
+ "content": "[unused30]",
509
+ "lstrip": false,
510
+ "normalized": true,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": false
514
+ },
515
+ "50316": {
516
+ "content": "[unused31]",
517
+ "lstrip": false,
518
+ "normalized": true,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": false
522
+ },
523
+ "50317": {
524
+ "content": "[unused32]",
525
+ "lstrip": false,
526
+ "normalized": true,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": false
530
+ },
531
+ "50318": {
532
+ "content": "[unused33]",
533
+ "lstrip": false,
534
+ "normalized": true,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": false
538
+ },
539
+ "50319": {
540
+ "content": "[unused34]",
541
+ "lstrip": false,
542
+ "normalized": true,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": false
546
+ },
547
+ "50320": {
548
+ "content": "[unused35]",
549
+ "lstrip": false,
550
+ "normalized": true,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": false
554
+ },
555
+ "50321": {
556
+ "content": "[unused36]",
557
+ "lstrip": false,
558
+ "normalized": true,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": false
562
+ },
563
+ "50322": {
564
+ "content": "[unused37]",
565
+ "lstrip": false,
566
+ "normalized": true,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": false
570
+ },
571
+ "50323": {
572
+ "content": "[unused38]",
573
+ "lstrip": false,
574
+ "normalized": true,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": false
578
+ },
579
+ "50324": {
580
+ "content": "[unused39]",
581
+ "lstrip": false,
582
+ "normalized": true,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": false
586
+ },
587
+ "50325": {
588
+ "content": "[unused40]",
589
+ "lstrip": false,
590
+ "normalized": true,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": false
594
+ },
595
+ "50326": {
596
+ "content": "[unused41]",
597
+ "lstrip": false,
598
+ "normalized": true,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": false
602
+ },
603
+ "50327": {
604
+ "content": "[unused42]",
605
+ "lstrip": false,
606
+ "normalized": true,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": false
610
+ },
611
+ "50328": {
612
+ "content": "[unused43]",
613
+ "lstrip": false,
614
+ "normalized": true,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": false
618
+ },
619
+ "50329": {
620
+ "content": "[unused44]",
621
+ "lstrip": false,
622
+ "normalized": true,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": false
626
+ },
627
+ "50330": {
628
+ "content": "[unused45]",
629
+ "lstrip": false,
630
+ "normalized": true,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": false
634
+ },
635
+ "50331": {
636
+ "content": "[unused46]",
637
+ "lstrip": false,
638
+ "normalized": true,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": false
642
+ },
643
+ "50332": {
644
+ "content": "[unused47]",
645
+ "lstrip": false,
646
+ "normalized": true,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": false
650
+ },
651
+ "50333": {
652
+ "content": "[unused48]",
653
+ "lstrip": false,
654
+ "normalized": true,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": false
658
+ },
659
+ "50334": {
660
+ "content": "[unused49]",
661
+ "lstrip": false,
662
+ "normalized": true,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": false
666
+ },
667
+ "50335": {
668
+ "content": "[unused50]",
669
+ "lstrip": false,
670
+ "normalized": true,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": false
674
+ },
675
+ "50336": {
676
+ "content": "[unused51]",
677
+ "lstrip": false,
678
+ "normalized": true,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": false
682
+ },
683
+ "50337": {
684
+ "content": "[unused52]",
685
+ "lstrip": false,
686
+ "normalized": true,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": false
690
+ },
691
+ "50338": {
692
+ "content": "[unused53]",
693
+ "lstrip": false,
694
+ "normalized": true,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": false
698
+ },
699
+ "50339": {
700
+ "content": "[unused54]",
701
+ "lstrip": false,
702
+ "normalized": true,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": false
706
+ },
707
+ "50340": {
708
+ "content": "[unused55]",
709
+ "lstrip": false,
710
+ "normalized": true,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": false
714
+ },
715
+ "50341": {
716
+ "content": "[unused56]",
717
+ "lstrip": false,
718
+ "normalized": true,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": false
722
+ },
723
+ "50342": {
724
+ "content": "[unused57]",
725
+ "lstrip": false,
726
+ "normalized": true,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": false
730
+ },
731
+ "50343": {
732
+ "content": "[unused58]",
733
+ "lstrip": false,
734
+ "normalized": true,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": false
738
+ },
739
+ "50344": {
740
+ "content": "[unused59]",
741
+ "lstrip": false,
742
+ "normalized": true,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": false
746
+ },
747
+ "50345": {
748
+ "content": "[unused60]",
749
+ "lstrip": false,
750
+ "normalized": true,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": false
754
+ },
755
+ "50346": {
756
+ "content": "[unused61]",
757
+ "lstrip": false,
758
+ "normalized": true,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": false
762
+ },
763
+ "50347": {
764
+ "content": "[unused62]",
765
+ "lstrip": false,
766
+ "normalized": true,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": false
770
+ },
771
+ "50348": {
772
+ "content": "[unused63]",
773
+ "lstrip": false,
774
+ "normalized": true,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": false
778
+ },
779
+ "50349": {
780
+ "content": "[unused64]",
781
+ "lstrip": false,
782
+ "normalized": true,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": false
786
+ },
787
+ "50350": {
788
+ "content": "[unused65]",
789
+ "lstrip": false,
790
+ "normalized": true,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": false
794
+ },
795
+ "50351": {
796
+ "content": "[unused66]",
797
+ "lstrip": false,
798
+ "normalized": true,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": false
802
+ },
803
+ "50352": {
804
+ "content": "[unused67]",
805
+ "lstrip": false,
806
+ "normalized": true,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": false
810
+ },
811
+ "50353": {
812
+ "content": "[unused68]",
813
+ "lstrip": false,
814
+ "normalized": true,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": false
818
+ },
819
+ "50354": {
820
+ "content": "[unused69]",
821
+ "lstrip": false,
822
+ "normalized": true,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": false
826
+ },
827
+ "50355": {
828
+ "content": "[unused70]",
829
+ "lstrip": false,
830
+ "normalized": true,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": false
834
+ },
835
+ "50356": {
836
+ "content": "[unused71]",
837
+ "lstrip": false,
838
+ "normalized": true,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": false
842
+ },
843
+ "50357": {
844
+ "content": "[unused72]",
845
+ "lstrip": false,
846
+ "normalized": true,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": false
850
+ },
851
+ "50358": {
852
+ "content": "[unused73]",
853
+ "lstrip": false,
854
+ "normalized": true,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": false
858
+ },
859
+ "50359": {
860
+ "content": "[unused74]",
861
+ "lstrip": false,
862
+ "normalized": true,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": false
866
+ },
867
+ "50360": {
868
+ "content": "[unused75]",
869
+ "lstrip": false,
870
+ "normalized": true,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": false
874
+ },
875
+ "50361": {
876
+ "content": "[unused76]",
877
+ "lstrip": false,
878
+ "normalized": true,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": false
882
+ },
883
+ "50362": {
884
+ "content": "[unused77]",
885
+ "lstrip": false,
886
+ "normalized": true,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": false
890
+ },
891
+ "50363": {
892
+ "content": "[unused78]",
893
+ "lstrip": false,
894
+ "normalized": true,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": false
898
+ },
899
+ "50364": {
900
+ "content": "[unused79]",
901
+ "lstrip": false,
902
+ "normalized": true,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": false
906
+ },
907
+ "50365": {
908
+ "content": "[unused80]",
909
+ "lstrip": false,
910
+ "normalized": true,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": false
914
+ },
915
+ "50366": {
916
+ "content": "[unused81]",
917
+ "lstrip": false,
918
+ "normalized": true,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": false
922
+ },
923
+ "50367": {
924
+ "content": "[unused82]",
925
+ "lstrip": false,
926
+ "normalized": true,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": false
930
+ }
931
+ },
932
+ "clean_up_tokenization_spaces": true,
933
+ "cls_token": "[CLS]",
934
+ "extra_special_tokens": {},
935
+ "mask_token": "[MASK]",
936
+ "max_length": 512,
937
+ "model_input_names": [
938
+ "input_ids",
939
+ "attention_mask"
940
+ ],
941
+ "model_max_length": 8192,
942
+ "pad_to_multiple_of": null,
943
+ "pad_token": "[PAD]",
944
+ "pad_token_type_id": 0,
945
+ "padding_side": "right",
946
+ "sep_token": "[SEP]",
947
+ "stride": 0,
948
+ "tokenizer_class": "PreTrainedTokenizerFast",
949
+ "truncation_side": "right",
950
+ "truncation_strategy": "longest_first",
951
+ "unk_token": "[UNK]"
952
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,945 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "|||IP_ADDRESS|||",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "1": {
12
+ "content": "<|padding|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "50254": {
20
+ "content": " ",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "50255": {
28
+ "content": " ",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "50256": {
36
+ "content": " ",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "50257": {
44
+ "content": " ",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "50258": {
52
+ "content": " ",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "50259": {
60
+ "content": " ",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "50260": {
68
+ "content": " ",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "50261": {
76
+ "content": " ",
77
+ "lstrip": false,
78
+ "normalized": true,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "50262": {
84
+ "content": " ",
85
+ "lstrip": false,
86
+ "normalized": true,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "50263": {
92
+ "content": " ",
93
+ "lstrip": false,
94
+ "normalized": true,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "50264": {
100
+ "content": " ",
101
+ "lstrip": false,
102
+ "normalized": true,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "50265": {
108
+ "content": " ",
109
+ "lstrip": false,
110
+ "normalized": true,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "50266": {
116
+ "content": " ",
117
+ "lstrip": false,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "50267": {
124
+ "content": " ",
125
+ "lstrip": false,
126
+ "normalized": true,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "50268": {
132
+ "content": " ",
133
+ "lstrip": false,
134
+ "normalized": true,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "50269": {
140
+ "content": " ",
141
+ "lstrip": false,
142
+ "normalized": true,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "50270": {
148
+ "content": " ",
149
+ "lstrip": false,
150
+ "normalized": true,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "50271": {
156
+ "content": " ",
157
+ "lstrip": false,
158
+ "normalized": true,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "50272": {
164
+ "content": " ",
165
+ "lstrip": false,
166
+ "normalized": true,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "50273": {
172
+ "content": " ",
173
+ "lstrip": false,
174
+ "normalized": true,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "50274": {
180
+ "content": " ",
181
+ "lstrip": false,
182
+ "normalized": true,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "50275": {
188
+ "content": " ",
189
+ "lstrip": false,
190
+ "normalized": true,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "50276": {
196
+ "content": " ",
197
+ "lstrip": false,
198
+ "normalized": true,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "50277": {
204
+ "content": "|||EMAIL_ADDRESS|||",
205
+ "lstrip": false,
206
+ "normalized": true,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "50278": {
212
+ "content": "|||PHONE_NUMBER|||",
213
+ "lstrip": false,
214
+ "normalized": true,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "50279": {
220
+ "content": "<|endoftext|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "50280": {
228
+ "content": "[UNK]",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "50281": {
236
+ "content": "[CLS]",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "50282": {
244
+ "content": "[SEP]",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "50283": {
252
+ "content": "[PAD]",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "50284": {
260
+ "content": "[MASK]",
261
+ "lstrip": true,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "50285": {
268
+ "content": "[unused0]",
269
+ "lstrip": false,
270
+ "normalized": true,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "50286": {
276
+ "content": "[unused1]",
277
+ "lstrip": false,
278
+ "normalized": true,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "50287": {
284
+ "content": "[unused2]",
285
+ "lstrip": false,
286
+ "normalized": true,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "50288": {
292
+ "content": "[unused3]",
293
+ "lstrip": false,
294
+ "normalized": true,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": false
298
+ },
299
+ "50289": {
300
+ "content": "[unused4]",
301
+ "lstrip": false,
302
+ "normalized": true,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": false
306
+ },
307
+ "50290": {
308
+ "content": "[unused5]",
309
+ "lstrip": false,
310
+ "normalized": true,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": false
314
+ },
315
+ "50291": {
316
+ "content": "[unused6]",
317
+ "lstrip": false,
318
+ "normalized": true,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": false
322
+ },
323
+ "50292": {
324
+ "content": "[unused7]",
325
+ "lstrip": false,
326
+ "normalized": true,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": false
330
+ },
331
+ "50293": {
332
+ "content": "[unused8]",
333
+ "lstrip": false,
334
+ "normalized": true,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": false
338
+ },
339
+ "50294": {
340
+ "content": "[unused9]",
341
+ "lstrip": false,
342
+ "normalized": true,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": false
346
+ },
347
+ "50295": {
348
+ "content": "[unused10]",
349
+ "lstrip": false,
350
+ "normalized": true,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": false
354
+ },
355
+ "50296": {
356
+ "content": "[unused11]",
357
+ "lstrip": false,
358
+ "normalized": true,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": false
362
+ },
363
+ "50297": {
364
+ "content": "[unused12]",
365
+ "lstrip": false,
366
+ "normalized": true,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": false
370
+ },
371
+ "50298": {
372
+ "content": "[unused13]",
373
+ "lstrip": false,
374
+ "normalized": true,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": false
378
+ },
379
+ "50299": {
380
+ "content": "[unused14]",
381
+ "lstrip": false,
382
+ "normalized": true,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": false
386
+ },
387
+ "50300": {
388
+ "content": "[unused15]",
389
+ "lstrip": false,
390
+ "normalized": true,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": false
394
+ },
395
+ "50301": {
396
+ "content": "[unused16]",
397
+ "lstrip": false,
398
+ "normalized": true,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": false
402
+ },
403
+ "50302": {
404
+ "content": "[unused17]",
405
+ "lstrip": false,
406
+ "normalized": true,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": false
410
+ },
411
+ "50303": {
412
+ "content": "[unused18]",
413
+ "lstrip": false,
414
+ "normalized": true,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": false
418
+ },
419
+ "50304": {
420
+ "content": "[unused19]",
421
+ "lstrip": false,
422
+ "normalized": true,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": false
426
+ },
427
+ "50305": {
428
+ "content": "[unused20]",
429
+ "lstrip": false,
430
+ "normalized": true,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": false
434
+ },
435
+ "50306": {
436
+ "content": "[unused21]",
437
+ "lstrip": false,
438
+ "normalized": true,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": false
442
+ },
443
+ "50307": {
444
+ "content": "[unused22]",
445
+ "lstrip": false,
446
+ "normalized": true,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": false
450
+ },
451
+ "50308": {
452
+ "content": "[unused23]",
453
+ "lstrip": false,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": false
458
+ },
459
+ "50309": {
460
+ "content": "[unused24]",
461
+ "lstrip": false,
462
+ "normalized": true,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": false
466
+ },
467
+ "50310": {
468
+ "content": "[unused25]",
469
+ "lstrip": false,
470
+ "normalized": true,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": false
474
+ },
475
+ "50311": {
476
+ "content": "[unused26]",
477
+ "lstrip": false,
478
+ "normalized": true,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": false
482
+ },
483
+ "50312": {
484
+ "content": "[unused27]",
485
+ "lstrip": false,
486
+ "normalized": true,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": false
490
+ },
491
+ "50313": {
492
+ "content": "[unused28]",
493
+ "lstrip": false,
494
+ "normalized": true,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": false
498
+ },
499
+ "50314": {
500
+ "content": "[unused29]",
501
+ "lstrip": false,
502
+ "normalized": true,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": false
506
+ },
507
+ "50315": {
508
+ "content": "[unused30]",
509
+ "lstrip": false,
510
+ "normalized": true,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": false
514
+ },
515
+ "50316": {
516
+ "content": "[unused31]",
517
+ "lstrip": false,
518
+ "normalized": true,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": false
522
+ },
523
+ "50317": {
524
+ "content": "[unused32]",
525
+ "lstrip": false,
526
+ "normalized": true,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": false
530
+ },
531
+ "50318": {
532
+ "content": "[unused33]",
533
+ "lstrip": false,
534
+ "normalized": true,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": false
538
+ },
539
+ "50319": {
540
+ "content": "[unused34]",
541
+ "lstrip": false,
542
+ "normalized": true,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": false
546
+ },
547
+ "50320": {
548
+ "content": "[unused35]",
549
+ "lstrip": false,
550
+ "normalized": true,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": false
554
+ },
555
+ "50321": {
556
+ "content": "[unused36]",
557
+ "lstrip": false,
558
+ "normalized": true,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": false
562
+ },
563
+ "50322": {
564
+ "content": "[unused37]",
565
+ "lstrip": false,
566
+ "normalized": true,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": false
570
+ },
571
+ "50323": {
572
+ "content": "[unused38]",
573
+ "lstrip": false,
574
+ "normalized": true,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": false
578
+ },
579
+ "50324": {
580
+ "content": "[unused39]",
581
+ "lstrip": false,
582
+ "normalized": true,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": false
586
+ },
587
+ "50325": {
588
+ "content": "[unused40]",
589
+ "lstrip": false,
590
+ "normalized": true,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": false
594
+ },
595
+ "50326": {
596
+ "content": "[unused41]",
597
+ "lstrip": false,
598
+ "normalized": true,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": false
602
+ },
603
+ "50327": {
604
+ "content": "[unused42]",
605
+ "lstrip": false,
606
+ "normalized": true,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": false
610
+ },
611
+ "50328": {
612
+ "content": "[unused43]",
613
+ "lstrip": false,
614
+ "normalized": true,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": false
618
+ },
619
+ "50329": {
620
+ "content": "[unused44]",
621
+ "lstrip": false,
622
+ "normalized": true,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": false
626
+ },
627
+ "50330": {
628
+ "content": "[unused45]",
629
+ "lstrip": false,
630
+ "normalized": true,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": false
634
+ },
635
+ "50331": {
636
+ "content": "[unused46]",
637
+ "lstrip": false,
638
+ "normalized": true,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": false
642
+ },
643
+ "50332": {
644
+ "content": "[unused47]",
645
+ "lstrip": false,
646
+ "normalized": true,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": false
650
+ },
651
+ "50333": {
652
+ "content": "[unused48]",
653
+ "lstrip": false,
654
+ "normalized": true,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": false
658
+ },
659
+ "50334": {
660
+ "content": "[unused49]",
661
+ "lstrip": false,
662
+ "normalized": true,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": false
666
+ },
667
+ "50335": {
668
+ "content": "[unused50]",
669
+ "lstrip": false,
670
+ "normalized": true,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": false
674
+ },
675
+ "50336": {
676
+ "content": "[unused51]",
677
+ "lstrip": false,
678
+ "normalized": true,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": false
682
+ },
683
+ "50337": {
684
+ "content": "[unused52]",
685
+ "lstrip": false,
686
+ "normalized": true,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": false
690
+ },
691
+ "50338": {
692
+ "content": "[unused53]",
693
+ "lstrip": false,
694
+ "normalized": true,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": false
698
+ },
699
+ "50339": {
700
+ "content": "[unused54]",
701
+ "lstrip": false,
702
+ "normalized": true,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": false
706
+ },
707
+ "50340": {
708
+ "content": "[unused55]",
709
+ "lstrip": false,
710
+ "normalized": true,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": false
714
+ },
715
+ "50341": {
716
+ "content": "[unused56]",
717
+ "lstrip": false,
718
+ "normalized": true,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": false
722
+ },
723
+ "50342": {
724
+ "content": "[unused57]",
725
+ "lstrip": false,
726
+ "normalized": true,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": false
730
+ },
731
+ "50343": {
732
+ "content": "[unused58]",
733
+ "lstrip": false,
734
+ "normalized": true,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": false
738
+ },
739
+ "50344": {
740
+ "content": "[unused59]",
741
+ "lstrip": false,
742
+ "normalized": true,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": false
746
+ },
747
+ "50345": {
748
+ "content": "[unused60]",
749
+ "lstrip": false,
750
+ "normalized": true,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": false
754
+ },
755
+ "50346": {
756
+ "content": "[unused61]",
757
+ "lstrip": false,
758
+ "normalized": true,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": false
762
+ },
763
+ "50347": {
764
+ "content": "[unused62]",
765
+ "lstrip": false,
766
+ "normalized": true,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": false
770
+ },
771
+ "50348": {
772
+ "content": "[unused63]",
773
+ "lstrip": false,
774
+ "normalized": true,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": false
778
+ },
779
+ "50349": {
780
+ "content": "[unused64]",
781
+ "lstrip": false,
782
+ "normalized": true,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": false
786
+ },
787
+ "50350": {
788
+ "content": "[unused65]",
789
+ "lstrip": false,
790
+ "normalized": true,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": false
794
+ },
795
+ "50351": {
796
+ "content": "[unused66]",
797
+ "lstrip": false,
798
+ "normalized": true,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": false
802
+ },
803
+ "50352": {
804
+ "content": "[unused67]",
805
+ "lstrip": false,
806
+ "normalized": true,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": false
810
+ },
811
+ "50353": {
812
+ "content": "[unused68]",
813
+ "lstrip": false,
814
+ "normalized": true,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": false
818
+ },
819
+ "50354": {
820
+ "content": "[unused69]",
821
+ "lstrip": false,
822
+ "normalized": true,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": false
826
+ },
827
+ "50355": {
828
+ "content": "[unused70]",
829
+ "lstrip": false,
830
+ "normalized": true,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": false
834
+ },
835
+ "50356": {
836
+ "content": "[unused71]",
837
+ "lstrip": false,
838
+ "normalized": true,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": false
842
+ },
843
+ "50357": {
844
+ "content": "[unused72]",
845
+ "lstrip": false,
846
+ "normalized": true,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": false
850
+ },
851
+ "50358": {
852
+ "content": "[unused73]",
853
+ "lstrip": false,
854
+ "normalized": true,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": false
858
+ },
859
+ "50359": {
860
+ "content": "[unused74]",
861
+ "lstrip": false,
862
+ "normalized": true,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": false
866
+ },
867
+ "50360": {
868
+ "content": "[unused75]",
869
+ "lstrip": false,
870
+ "normalized": true,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": false
874
+ },
875
+ "50361": {
876
+ "content": "[unused76]",
877
+ "lstrip": false,
878
+ "normalized": true,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": false
882
+ },
883
+ "50362": {
884
+ "content": "[unused77]",
885
+ "lstrip": false,
886
+ "normalized": true,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": false
890
+ },
891
+ "50363": {
892
+ "content": "[unused78]",
893
+ "lstrip": false,
894
+ "normalized": true,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": false
898
+ },
899
+ "50364": {
900
+ "content": "[unused79]",
901
+ "lstrip": false,
902
+ "normalized": true,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": false
906
+ },
907
+ "50365": {
908
+ "content": "[unused80]",
909
+ "lstrip": false,
910
+ "normalized": true,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": false
914
+ },
915
+ "50366": {
916
+ "content": "[unused81]",
917
+ "lstrip": false,
918
+ "normalized": true,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": false
922
+ },
923
+ "50367": {
924
+ "content": "[unused82]",
925
+ "lstrip": false,
926
+ "normalized": true,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": false
930
+ }
931
+ },
932
+ "clean_up_tokenization_spaces": true,
933
+ "cls_token": "[CLS]",
934
+ "extra_special_tokens": {},
935
+ "mask_token": "[MASK]",
936
+ "model_input_names": [
937
+ "input_ids",
938
+ "attention_mask"
939
+ ],
940
+ "model_max_length": 8192,
941
+ "pad_token": "[PAD]",
942
+ "sep_token": "[SEP]",
943
+ "tokenizer_class": "PreTrainedTokenizerFast",
944
+ "unk_token": "[UNK]"
945
+ }
training_metadata.json ADDED
@@ -0,0 +1,241 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attn_implementation": "eager",
3
+ "early_stopping_patience": 2,
4
+ "early_stopping_threshold": 0.0,
5
+ "eval_rows": 9495,
6
+ "id2label": {
7
+ "0": "Julia",
8
+ "1": "Go",
9
+ "2": "Raku",
10
+ "3": "Pascal",
11
+ "4": "Perl",
12
+ "5": "Python",
13
+ "6": "Nim",
14
+ "7": "J",
15
+ "8": "C",
16
+ "9": "Haskell",
17
+ "10": "Mathematica/Wolfram Language",
18
+ "11": "Kotlin",
19
+ "12": "Java",
20
+ "13": "Ruby",
21
+ "14": "Racket",
22
+ "15": "C++",
23
+ "16": "Tcl",
24
+ "17": "C#",
25
+ "18": "Scala",
26
+ "19": "Ada",
27
+ "20": "Factor",
28
+ "21": "Rust",
29
+ "22": "Lua",
30
+ "23": "D",
31
+ "24": "Common Lisp",
32
+ "25": "AutoHotkey",
33
+ "26": "JavaScript",
34
+ "27": "F#",
35
+ "28": "Wren",
36
+ "29": "Clojure",
37
+ "30": "Fortran",
38
+ "31": "PureBasic",
39
+ "32": "OCaml",
40
+ "33": "Awk",
41
+ "34": "R",
42
+ "35": "Swift",
43
+ "36": "Forth",
44
+ "37": "Elixir",
45
+ "38": "Erlang",
46
+ "39": "PowerShell",
47
+ "40": "Groovy",
48
+ "41": "REXX",
49
+ "42": "Visual Basic .NET",
50
+ "43": "PHP",
51
+ "44": "Prolog",
52
+ "45": "Scheme",
53
+ "46": "AppleScript",
54
+ "47": "COBOL",
55
+ "48": "FreeBASIC",
56
+ "49": "Smalltalk",
57
+ "50": "PicoLisp",
58
+ "51": "MATLAB",
59
+ "52": "Oz",
60
+ "53": "Standard ML",
61
+ "54": "Lasso",
62
+ "55": "Crystal",
63
+ "56": "APL",
64
+ "57": "Stata",
65
+ "58": "CoffeeScript",
66
+ "59": "Batchfile",
67
+ "60": "jq",
68
+ "61": "GAP",
69
+ "62": "Red",
70
+ "63": "Emacs Lisp",
71
+ "64": "Eiffel",
72
+ "65": "Fantom",
73
+ "66": "Ring",
74
+ "67": "Pike",
75
+ "68": "Rebol",
76
+ "69": "ActionScript",
77
+ "70": "MAXScript",
78
+ "71": "Vala",
79
+ "72": "Dart",
80
+ "73": "Processing",
81
+ "74": "Ceylon",
82
+ "75": "AutoIt",
83
+ "76": "Io",
84
+ "77": "M4",
85
+ "78": "Zig",
86
+ "79": "LFE",
87
+ "80": "ATS",
88
+ "81": "Logtalk",
89
+ "82": "ABAP",
90
+ "83": "Scilab",
91
+ "84": "IDL",
92
+ "85": "LabVIEW",
93
+ "86": "ColdFusion",
94
+ "87": "SAS",
95
+ "88": "Haxe",
96
+ "89": "VBA",
97
+ "90": "BASIC",
98
+ "91": "V",
99
+ "92": "VBScript",
100
+ "93": "E",
101
+ "94": "Euphoria",
102
+ "95": "ARM Assembly",
103
+ "96": "Component Pascal",
104
+ "97": "M",
105
+ "98": "Modula-2",
106
+ "99": "BQN",
107
+ "100": "Befunge",
108
+ "101": "Objective-C",
109
+ "102": "NewLisp",
110
+ "103": "Nemerle",
111
+ "104": "Modula-3",
112
+ "105": "Mercury",
113
+ "106": "QuickBASIC"
114
+ },
115
+ "label2id": {
116
+ "ABAP": 82,
117
+ "APL": 56,
118
+ "ARM Assembly": 95,
119
+ "ATS": 80,
120
+ "ActionScript": 69,
121
+ "Ada": 19,
122
+ "AppleScript": 46,
123
+ "AutoHotkey": 25,
124
+ "AutoIt": 75,
125
+ "Awk": 33,
126
+ "BASIC": 90,
127
+ "BQN": 99,
128
+ "Batchfile": 59,
129
+ "Befunge": 100,
130
+ "C": 8,
131
+ "C#": 17,
132
+ "C++": 15,
133
+ "COBOL": 47,
134
+ "Ceylon": 74,
135
+ "Clojure": 29,
136
+ "CoffeeScript": 58,
137
+ "ColdFusion": 86,
138
+ "Common Lisp": 24,
139
+ "Component Pascal": 96,
140
+ "Crystal": 55,
141
+ "D": 23,
142
+ "Dart": 72,
143
+ "E": 93,
144
+ "Eiffel": 64,
145
+ "Elixir": 37,
146
+ "Emacs Lisp": 63,
147
+ "Erlang": 38,
148
+ "Euphoria": 94,
149
+ "F#": 27,
150
+ "Factor": 20,
151
+ "Fantom": 65,
152
+ "Forth": 36,
153
+ "Fortran": 30,
154
+ "FreeBASIC": 48,
155
+ "GAP": 61,
156
+ "Go": 1,
157
+ "Groovy": 40,
158
+ "Haskell": 9,
159
+ "Haxe": 88,
160
+ "IDL": 84,
161
+ "Io": 76,
162
+ "J": 7,
163
+ "Java": 12,
164
+ "JavaScript": 26,
165
+ "Julia": 0,
166
+ "Kotlin": 11,
167
+ "LFE": 79,
168
+ "LabVIEW": 85,
169
+ "Lasso": 54,
170
+ "Logtalk": 81,
171
+ "Lua": 22,
172
+ "M": 97,
173
+ "M4": 77,
174
+ "MATLAB": 51,
175
+ "MAXScript": 70,
176
+ "Mathematica/Wolfram Language": 10,
177
+ "Mercury": 105,
178
+ "Modula-2": 98,
179
+ "Modula-3": 104,
180
+ "Nemerle": 103,
181
+ "NewLisp": 102,
182
+ "Nim": 6,
183
+ "OCaml": 32,
184
+ "Objective-C": 101,
185
+ "Oz": 52,
186
+ "PHP": 43,
187
+ "Pascal": 3,
188
+ "Perl": 4,
189
+ "PicoLisp": 50,
190
+ "Pike": 67,
191
+ "PowerShell": 39,
192
+ "Processing": 73,
193
+ "Prolog": 44,
194
+ "PureBasic": 31,
195
+ "Python": 5,
196
+ "QuickBASIC": 106,
197
+ "R": 34,
198
+ "REXX": 41,
199
+ "Racket": 14,
200
+ "Raku": 2,
201
+ "Rebol": 68,
202
+ "Red": 62,
203
+ "Ring": 66,
204
+ "Ruby": 13,
205
+ "Rust": 21,
206
+ "SAS": 87,
207
+ "Scala": 18,
208
+ "Scheme": 45,
209
+ "Scilab": 83,
210
+ "Smalltalk": 49,
211
+ "Standard ML": 53,
212
+ "Stata": 57,
213
+ "Swift": 35,
214
+ "Tcl": 16,
215
+ "V": 91,
216
+ "VBA": 89,
217
+ "VBScript": 92,
218
+ "Vala": 71,
219
+ "Visual Basic .NET": 42,
220
+ "Wren": 28,
221
+ "Zig": 78,
222
+ "jq": 60
223
+ },
224
+ "learning_rate": 2e-05,
225
+ "lr_scheduler_type": "linear",
226
+ "model_name": "answerdotai/ModernBERT-base",
227
+ "num_labels": 107,
228
+ "num_train_epochs": 10.0,
229
+ "snippet_config": {
230
+ "eval_strategy": "head",
231
+ "max_chars": 512,
232
+ "min_chars": 64,
233
+ "seed": 20260420,
234
+ "short_chars": 128,
235
+ "train_strategies": [
236
+ "variable_window"
237
+ ]
238
+ },
239
+ "train_rows": 72549,
240
+ "warmup_ratio": 0.06
241
+ }