justin-bec commited on
Commit
38642e3
·
verified ·
1 Parent(s): 112a835

Chess Challenge submission by justin-bec

Browse files
Files changed (6) hide show
  1. README.md +26 -0
  2. config.json +20 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +6 -0
  5. tokenizer_config.json +44 -0
  6. vocab.json +439 -0
README.md ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - chess
5
+ - llm-course
6
+ - chess-challenge
7
+ license: mit
8
+ ---
9
+
10
+ # justin_second_try
11
+
12
+ Chess model submitted to the LLM Course Chess Challenge.
13
+
14
+ ## Submission Info
15
+
16
+ - **Submitted by**: [justin-bec](https://huggingface.co/justin-bec)
17
+ - **Parameters**: 998,080
18
+ - **Organization**: LLM-course
19
+
20
+ ## Model Details
21
+
22
+ - **Architecture**: Chess Transformer (GPT-style)
23
+ - **Vocab size**: 437
24
+ - **Embedding dim**: 128
25
+ - **Layers**: 5
26
+ - **Heads**: 4
config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ChessForCausalLM"
4
+ ],
5
+ "bos_token_id": 1,
6
+ "dropout": 0.1,
7
+ "dtype": "float32",
8
+ "eos_token_id": 2,
9
+ "layer_norm_epsilon": 1e-05,
10
+ "model_type": "chess_transformer",
11
+ "n_ctx": 256,
12
+ "n_embd": 128,
13
+ "n_head": 4,
14
+ "n_inner": 448,
15
+ "n_layer": 5,
16
+ "pad_token_id": 0,
17
+ "tie_weights": true,
18
+ "transformers_version": "4.57.6",
19
+ "vocab_size": 437
20
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:737e43a6c200266d98e2bd427d5f5a81d40cedc837635186a802c4b2e0b196af
3
+ size 3997744
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[BOS]",
3
+ "eos_token": "[EOS]",
4
+ "pad_token": "[PAD]",
5
+ "unk_token": "[UNK]"
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[BOS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[EOS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "bos_token": "[BOS]",
37
+ "clean_up_tokenization_spaces": false,
38
+ "eos_token": "[EOS]",
39
+ "extra_special_tokens": {},
40
+ "model_max_length": 1000000000000000019884624838656,
41
+ "pad_token": "[PAD]",
42
+ "tokenizer_class": "ChessTokenizer",
43
+ "unk_token": "[UNK]"
44
+ }
vocab.json ADDED
@@ -0,0 +1,439 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD]": 0,
3
+ "[BOS]": 1,
4
+ "[EOS]": 2,
5
+ "[UNK]": 3,
6
+ "BBb4a5": 4,
7
+ "BBb4c3(x)": 5,
8
+ "BBb4c3(x+)": 6,
9
+ "BBc5b6": 7,
10
+ "BBc8a6": 8,
11
+ "BBc8b7": 9,
12
+ "BBc8d7": 10,
13
+ "BBc8e6": 11,
14
+ "BBc8f5": 12,
15
+ "BBc8g4": 13,
16
+ "BBd6e5(x)": 14,
17
+ "BBd6e7": 15,
18
+ "BBd7c6": 16,
19
+ "BBe7d6": 17,
20
+ "BBe7f6": 18,
21
+ "BBe7f6(x)": 19,
22
+ "BBf5d3(x)": 20,
23
+ "BBf5g6": 21,
24
+ "BBf8b4": 22,
25
+ "BBf8b4(+)": 23,
26
+ "BBf8c5": 24,
27
+ "BBf8c5(x)": 25,
28
+ "BBf8d6": 26,
29
+ "BBf8e7": 27,
30
+ "BBf8g7": 28,
31
+ "BBg4f3(x)": 29,
32
+ "BBg4h5": 30,
33
+ "BBg7e5(x)": 31,
34
+ "BBg7f6(x)": 32,
35
+ "BBh5g6": 33,
36
+ "BKc8b8": 34,
37
+ "BKc8d7": 35,
38
+ "BKd7c6": 36,
39
+ "BKe7d6": 37,
40
+ "BKe7d7": 38,
41
+ "BKe7f6": 39,
42
+ "BKe8c8(O)": 40,
43
+ "BKe8d7": 41,
44
+ "BKe8d8": 42,
45
+ "BKe8e7": 43,
46
+ "BKe8f7": 44,
47
+ "BKe8f7(x)": 45,
48
+ "BKe8f8": 46,
49
+ "BKe8g8(o)": 47,
50
+ "BKf7e6": 48,
51
+ "BKf7e7": 49,
52
+ "BKf7f6": 50,
53
+ "BKf7g6": 51,
54
+ "BKf7g8": 52,
55
+ "BKf8e7": 53,
56
+ "BKf8g7": 54,
57
+ "BKf8g8": 55,
58
+ "BKg7f6": 56,
59
+ "BKg7g6": 57,
60
+ "BKg7h6": 58,
61
+ "BKg8f7": 59,
62
+ "BKg8f8": 60,
63
+ "BKg8g7": 61,
64
+ "BKg8g7(x)": 62,
65
+ "BKg8h7": 63,
66
+ "BKg8h8": 64,
67
+ "BKh7g6": 65,
68
+ "BKh7g8": 66,
69
+ "BKh8g8": 67,
70
+ "BKh8h7": 68,
71
+ "BNb8a6": 69,
72
+ "BNb8c6": 70,
73
+ "BNb8d7": 71,
74
+ "BNc6a5": 72,
75
+ "BNc6b4": 73,
76
+ "BNc6d4": 74,
77
+ "BNc6d4(x)": 75,
78
+ "BNc6e5": 76,
79
+ "BNc6e5(x)": 77,
80
+ "BNc6e7": 78,
81
+ "BNd5c3(x)": 79,
82
+ "BNd7b6": 80,
83
+ "BNd7c5": 81,
84
+ "BNd7e5": 82,
85
+ "BNd7e5(x)": 83,
86
+ "BNd7f6": 84,
87
+ "BNe4c3(x)": 85,
88
+ "BNe4f6": 86,
89
+ "BNe7c6": 87,
90
+ "BNe7d5": 88,
91
+ "BNe7f5": 89,
92
+ "BNe7g6": 90,
93
+ "BNf6d5": 91,
94
+ "BNf6d5(x)": 92,
95
+ "BNf6d7": 93,
96
+ "BNf6e4": 94,
97
+ "BNf6e4(x)": 95,
98
+ "BNf6e8": 96,
99
+ "BNf6g4": 97,
100
+ "BNf6g4(x)": 98,
101
+ "BNf6h5": 99,
102
+ "BNg8e7": 100,
103
+ "BNg8f6": 101,
104
+ "BNg8h6": 102,
105
+ "BPa3a2": 103,
106
+ "BPa4a3": 104,
107
+ "BPa5a4": 105,
108
+ "BPa5b4(x)": 106,
109
+ "BPa6a5": 107,
110
+ "BPa6b5(x)": 108,
111
+ "BPa7a5": 109,
112
+ "BPa7a6": 110,
113
+ "BPa7b6(x)": 111,
114
+ "BPb4b3": 112,
115
+ "BPb5b4": 113,
116
+ "BPb5c4(x)": 114,
117
+ "BPb6b5": 115,
118
+ "BPb6c5(x)": 116,
119
+ "BPb7b5": 117,
120
+ "BPb7b6": 118,
121
+ "BPb7c6(x)": 119,
122
+ "BPc4c3": 120,
123
+ "BPc5c4": 121,
124
+ "BPc5d4(x)": 122,
125
+ "BPc6b5(x)": 123,
126
+ "BPc6c5": 124,
127
+ "BPc6d5(x)": 125,
128
+ "BPc7c5": 126,
129
+ "BPc7c6": 127,
130
+ "BPc7d6(x)": 128,
131
+ "BPd4c3(x)": 129,
132
+ "BPd4d3": 130,
133
+ "BPd5c4(x)": 131,
134
+ "BPd5d4": 132,
135
+ "BPd5e4(x)": 133,
136
+ "BPd6c5(x)": 134,
137
+ "BPd6d5": 135,
138
+ "BPd6e5(x)": 136,
139
+ "BPd7d5": 137,
140
+ "BPd7d6": 138,
141
+ "BPe4e3": 139,
142
+ "BPe4f3(x)": 140,
143
+ "BPe5d4(x)": 141,
144
+ "BPe5e4": 142,
145
+ "BPe5f4(x)": 143,
146
+ "BPe6d5(x)": 144,
147
+ "BPe6e5": 145,
148
+ "BPe6f5(x)": 146,
149
+ "BPe7e5": 147,
150
+ "BPe7e6": 148,
151
+ "BPf4f3": 149,
152
+ "BPf5e4(x)": 150,
153
+ "BPf5f4": 151,
154
+ "BPf6e5(x)": 152,
155
+ "BPf6f5": 153,
156
+ "BPf7e6(x)": 154,
157
+ "BPf7f5": 155,
158
+ "BPf7f6": 156,
159
+ "BPf7g6(x)": 157,
160
+ "BPg4g3": 158,
161
+ "BPg5f4(x)": 159,
162
+ "BPg5g4": 160,
163
+ "BPg6f5(x)": 161,
164
+ "BPg6g5": 162,
165
+ "BPg7f6(x)": 163,
166
+ "BPg7g5": 164,
167
+ "BPg7g6": 165,
168
+ "BPh4h3": 166,
169
+ "BPh5g4(x)": 167,
170
+ "BPh5h4": 168,
171
+ "BPh6g5(x)": 169,
172
+ "BPh6h5": 170,
173
+ "BPh7g6(x)": 171,
174
+ "BPh7h5": 172,
175
+ "BPh7h6": 173,
176
+ "BQd8a5": 174,
177
+ "BQd8b6": 175,
178
+ "BQd8c7": 176,
179
+ "BQd8c8": 177,
180
+ "BQd8d5(x)": 178,
181
+ "BQd8d6": 179,
182
+ "BQd8d7": 180,
183
+ "BQd8e7": 181,
184
+ "BQd8e7(x)": 182,
185
+ "BQd8e8": 183,
186
+ "BQd8f6": 184,
187
+ "BQd8f6(x)": 185,
188
+ "BQd8h4": 186,
189
+ "BQf6g6": 187,
190
+ "BRa8b8": 188,
191
+ "BRa8c8": 189,
192
+ "BRa8d8": 190,
193
+ "BRa8e8": 191,
194
+ "BRa8f8": 192,
195
+ "BRc8d8": 193,
196
+ "BRd8c8": 194,
197
+ "BRd8d7": 195,
198
+ "BRd8e8": 196,
199
+ "BRd8f8": 197,
200
+ "BRe8d8": 198,
201
+ "BRe8e7": 199,
202
+ "BRe8f8": 200,
203
+ "BRf8b8": 201,
204
+ "BRf8c8": 202,
205
+ "BRf8d8": 203,
206
+ "BRf8e8": 204,
207
+ "BRf8f7": 205,
208
+ "BRf8g8": 206,
209
+ "BRh8d8": 207,
210
+ "BRh8e8": 208,
211
+ "BRh8f8": 209,
212
+ "BRh8g8": 210,
213
+ "WBb5a4": 211,
214
+ "WBb5c6(x)": 212,
215
+ "WBb5c6(x+)": 213,
216
+ "WBb5d7(x+)": 214,
217
+ "WBc1a3": 215,
218
+ "WBc1b2": 216,
219
+ "WBc1d2": 217,
220
+ "WBc1e3": 218,
221
+ "WBc1f4": 219,
222
+ "WBc1f4(x)": 220,
223
+ "WBc1g5": 221,
224
+ "WBc4b3": 222,
225
+ "WBc4d3": 223,
226
+ "WBc4d5(x)": 224,
227
+ "WBc4e6(x)": 225,
228
+ "WBc4f7(x+)": 226,
229
+ "WBd2c3": 227,
230
+ "WBd2e3": 228,
231
+ "WBd3c2": 229,
232
+ "WBd3e2": 230,
233
+ "WBd3e4(x)": 231,
234
+ "WBd3f5(x)": 232,
235
+ "WBe2d3": 233,
236
+ "WBe2f3": 234,
237
+ "WBe2f3(x)": 235,
238
+ "WBe3c5(x)": 236,
239
+ "WBe3d2": 237,
240
+ "WBe3d4": 238,
241
+ "WBe3d4(x)": 239,
242
+ "WBe3g5": 240,
243
+ "WBf1b5": 241,
244
+ "WBf1b5(+)": 242,
245
+ "WBf1c4": 243,
246
+ "WBf1c4(x)": 244,
247
+ "WBf1d3": 245,
248
+ "WBf1e2": 246,
249
+ "WBf1g2": 247,
250
+ "WBf4d6(x)": 248,
251
+ "WBf4e3": 249,
252
+ "WBf4e5(x)": 250,
253
+ "WBf4g3": 251,
254
+ "WBg5e3": 252,
255
+ "WBg5e7(x)": 253,
256
+ "WBg5f4": 254,
257
+ "WBg5f6(x)": 255,
258
+ "WBg5h4": 256,
259
+ "WBh4g3": 257,
260
+ "WKc1b1": 258,
261
+ "WKc1d2": 259,
262
+ "WKe1c1(O)": 260,
263
+ "WKe1d1": 261,
264
+ "WKe1d2": 262,
265
+ "WKe1e2": 263,
266
+ "WKe1f1": 264,
267
+ "WKe1f2": 265,
268
+ "WKe1g1(o)": 266,
269
+ "WKe2d2": 267,
270
+ "WKe2d3": 268,
271
+ "WKf1e2": 269,
272
+ "WKf1g1": 270,
273
+ "WKf2e2": 271,
274
+ "WKf2e3": 272,
275
+ "WKf2f3": 273,
276
+ "WKf2g3": 274,
277
+ "WKg1f1": 275,
278
+ "WKg1f2": 276,
279
+ "WKg1g2": 277,
280
+ "WKg1h1": 278,
281
+ "WKg1h2": 279,
282
+ "WKg2f3": 280,
283
+ "WKg2g3": 281,
284
+ "WKg2h3": 282,
285
+ "WKh1g1": 283,
286
+ "WKh1h2": 284,
287
+ "WKh2g1": 285,
288
+ "WKh2g3": 286,
289
+ "WNb1a3": 287,
290
+ "WNb1c3": 288,
291
+ "WNb1d2": 289,
292
+ "WNc3a4": 290,
293
+ "WNc3b5": 291,
294
+ "WNc3d5": 292,
295
+ "WNc3d5(x)": 293,
296
+ "WNc3e2": 294,
297
+ "WNc3e4": 295,
298
+ "WNc3e4(x)": 296,
299
+ "WNd2b3": 297,
300
+ "WNd2c4": 298,
301
+ "WNd2e4": 299,
302
+ "WNd2e4(x)": 300,
303
+ "WNd2f1": 301,
304
+ "WNd2f3": 302,
305
+ "WNd4c6(x)": 303,
306
+ "WNd4f3": 304,
307
+ "WNe2f4": 305,
308
+ "WNe2g3": 306,
309
+ "WNe4f6(x+)": 307,
310
+ "WNe5c6(x)": 308,
311
+ "WNe5d7(x)": 309,
312
+ "WNe5f3": 310,
313
+ "WNf3d2": 311,
314
+ "WNf3d4": 312,
315
+ "WNf3d4(x)": 313,
316
+ "WNf3e5": 314,
317
+ "WNf3e5(x)": 315,
318
+ "WNf3g5": 316,
319
+ "WNf3g5(x)": 317,
320
+ "WNf3h2": 318,
321
+ "WNf3h4": 319,
322
+ "WNg1e2": 320,
323
+ "WNg1f3": 321,
324
+ "WNg1h3": 322,
325
+ "WNg5f3": 323,
326
+ "WPa2a3": 324,
327
+ "WPa2a4": 325,
328
+ "WPa2b3(x)": 326,
329
+ "WPa3a4": 327,
330
+ "WPa3b4(x)": 328,
331
+ "WPa4a5": 329,
332
+ "WPa4b5(x)": 330,
333
+ "WPa5a6": 331,
334
+ "WPa6a7": 332,
335
+ "WPb2b3": 333,
336
+ "WPb2b4": 334,
337
+ "WPb2c3(x)": 335,
338
+ "WPb3b4": 336,
339
+ "WPb3c4(x)": 337,
340
+ "WPb4b5": 338,
341
+ "WPb4c5(x)": 339,
342
+ "WPb5b6": 340,
343
+ "WPc2c3": 341,
344
+ "WPc2c4": 342,
345
+ "WPc2d3(x)": 343,
346
+ "WPc3b4(x)": 344,
347
+ "WPc3c4": 345,
348
+ "WPc3d4(x)": 346,
349
+ "WPc4b5(x)": 347,
350
+ "WPc4c5": 348,
351
+ "WPc4d5(x)": 349,
352
+ "WPc5c6": 350,
353
+ "WPd2d3": 351,
354
+ "WPd2d4": 352,
355
+ "WPd3d4": 353,
356
+ "WPd3e4(x)": 354,
357
+ "WPd4c5(x)": 355,
358
+ "WPd4d5": 356,
359
+ "WPd4e5(x)": 357,
360
+ "WPd5c6(x)": 358,
361
+ "WPd5d6": 359,
362
+ "WPd5e6(x)": 360,
363
+ "WPe2e3": 361,
364
+ "WPe2e4": 362,
365
+ "WPe3d4(x)": 363,
366
+ "WPe3e4": 364,
367
+ "WPe4d5(x)": 365,
368
+ "WPe4e5": 366,
369
+ "WPe4f5(x)": 367,
370
+ "WPe5d6(x)": 368,
371
+ "WPe5e6": 369,
372
+ "WPe5f6(x)": 370,
373
+ "WPf2e3(x)": 371,
374
+ "WPf2f3": 372,
375
+ "WPf2f4": 373,
376
+ "WPf2g3(x)": 374,
377
+ "WPf3e4(x)": 375,
378
+ "WPf3f4": 376,
379
+ "WPf4e5(x)": 377,
380
+ "WPf4f5": 378,
381
+ "WPf5f6": 379,
382
+ "WPg2f3(x)": 380,
383
+ "WPg2g3": 381,
384
+ "WPg2g4": 382,
385
+ "WPg3f4(x)": 383,
386
+ "WPg3g4": 384,
387
+ "WPg4f5(x)": 385,
388
+ "WPg4g5": 386,
389
+ "WPg5g6": 387,
390
+ "WPh2g3(x)": 388,
391
+ "WPh2h3": 389,
392
+ "WPh2h4": 390,
393
+ "WPh3g4(x)": 391,
394
+ "WPh3h4": 392,
395
+ "WPh4g5(x)": 393,
396
+ "WPh4h5": 394,
397
+ "WPh5g6(x)": 395,
398
+ "WPh5h6": 396,
399
+ "WQd1a4": 397,
400
+ "WQd1b3": 398,
401
+ "WQd1c2": 399,
402
+ "WQd1d2": 400,
403
+ "WQd1d3": 401,
404
+ "WQd1d3(x)": 402,
405
+ "WQd1d4(x)": 403,
406
+ "WQd1e1": 404,
407
+ "WQd1e2": 405,
408
+ "WQd1f3": 406,
409
+ "WQd1f3(x)": 407,
410
+ "WQd1g4": 408,
411
+ "WQd1h5": 409,
412
+ "WQf3g3": 410,
413
+ "WRa1b1": 411,
414
+ "WRa1c1": 412,
415
+ "WRa1d1": 413,
416
+ "WRa1e1": 414,
417
+ "WRa1f1": 415,
418
+ "WRc1d1": 416,
419
+ "WRd1c1": 417,
420
+ "WRd1d2": 418,
421
+ "WRd1e1": 419,
422
+ "WRd1f1": 420,
423
+ "WRe1d1": 421,
424
+ "WRe1e2": 422,
425
+ "WRe1e3": 423,
426
+ "WRe1e4(x)": 424,
427
+ "WRe1e5(x)": 425,
428
+ "WRe1f1": 426,
429
+ "WRf1c1": 427,
430
+ "WRf1d1": 428,
431
+ "WRf1e1": 429,
432
+ "WRf1f2": 430,
433
+ "WRf1f3": 431,
434
+ "WRf1g1": 432,
435
+ "WRh1d1": 433,
436
+ "WRh1e1": 434,
437
+ "WRh1f1": 435,
438
+ "WRh1g1": 436
439
+ }