Hugging Face's logo

LLM-course
/
Sunxt25

Text Generation
Transformers
Safetensors
chess_transformer
chess
llm-course
chess-challenge
Model card Files
xet
Community
Sunxt25 commited on
Commit
1d59071
·
verified ·
1 Parent(s): 8ad6bed

Chess Challenge submission by Sunxt25

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 +146 -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
+ # Sunxt25
11
+
12
+ Chess model submitted to the LLM Course Chess Challenge.
13
+
14
+ ## Submission Info
15
+
16
+ - **Submitted by**: [Sunxt25](https://huggingface.co/Sunxt25)
17
+ - **Parameters**: 878,336
18
+ - **Organization**: LLM-course
19
+
20
+ ## Model Details
21
+
22
+ - **Architecture**: Chess Transformer (GPT-style)
23
+ - **Vocab size**: 144
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": 384,
15
+ "n_layer": 5,
16
+ "pad_token_id": 0,
17
+ "tie_weights": true,
18
+ "transformers_version": "4.57.5",
19
+ "vocab_size": 144
20
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2b168eb150974e5eff71ecdc4c7dc06a708917e31fc17001362a4550da9da07
3
+ size 3518768
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 +1,146 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD]": 0,
3
+ "[BOS]": 1,
4
+ "[EOS]": 2,
5
+ "[UNK]": 3,
6
+ "WP": 4,
7
+ "WN": 5,
8
+ "WB": 6,
9
+ "WR": 7,
10
+ "WQ": 8,
11
+ "WK": 9,
12
+ "BP": 10,
13
+ "BN": 11,
14
+ "BB": 12,
15
+ "BR": 13,
16
+ "BQ": 14,
17
+ "BK": 15,
18
+ "a1_f": 16,
19
+ "b1_f": 17,
20
+ "c1_f": 18,
21
+ "d1_f": 19,
22
+ "e1_f": 20,
23
+ "f1_f": 21,
24
+ "g1_f": 22,
25
+ "h1_f": 23,
26
+ "a2_f": 24,
27
+ "b2_f": 25,
28
+ "c2_f": 26,
29
+ "d2_f": 27,
30
+ "e2_f": 28,
31
+ "f2_f": 29,
32
+ "g2_f": 30,
33
+ "h2_f": 31,
34
+ "a3_f": 32,
35
+ "b3_f": 33,
36
+ "c3_f": 34,
37
+ "d3_f": 35,
38
+ "e3_f": 36,
39
+ "f3_f": 37,
40
+ "g3_f": 38,
41
+ "h3_f": 39,
42
+ "a4_f": 40,
43
+ "b4_f": 41,
44
+ "c4_f": 42,
45
+ "d4_f": 43,
46
+ "e4_f": 44,
47
+ "f4_f": 45,
48
+ "g4_f": 46,
49
+ "h4_f": 47,
50
+ "a5_f": 48,
51
+ "b5_f": 49,
52
+ "c5_f": 50,
53
+ "d5_f": 51,
54
+ "e5_f": 52,
55
+ "f5_f": 53,
56
+ "g5_f": 54,
57
+ "h5_f": 55,
58
+ "a6_f": 56,
59
+ "b6_f": 57,
60
+ "c6_f": 58,
61
+ "d6_f": 59,
62
+ "e6_f": 60,
63
+ "f6_f": 61,
64
+ "g6_f": 62,
65
+ "h6_f": 63,
66
+ "a7_f": 64,
67
+ "b7_f": 65,
68
+ "c7_f": 66,
69
+ "d7_f": 67,
70
+ "e7_f": 68,
71
+ "f7_f": 69,
72
+ "g7_f": 70,
73
+ "h7_f": 71,
74
+ "a8_f": 72,
75
+ "b8_f": 73,
76
+ "c8_f": 74,
77
+ "d8_f": 75,
78
+ "e8_f": 76,
79
+ "f8_f": 77,
80
+ "g8_f": 78,
81
+ "h8_f": 79,
82
+ "a1_t": 80,
83
+ "b1_t": 81,
84
+ "c1_t": 82,
85
+ "d1_t": 83,
86
+ "e1_t": 84,
87
+ "f1_t": 85,
88
+ "g1_t": 86,
89
+ "h1_t": 87,
90
+ "a2_t": 88,
91
+ "b2_t": 89,
92
+ "c2_t": 90,
93
+ "d2_t": 91,
94
+ "e2_t": 92,
95
+ "f2_t": 93,
96
+ "g2_t": 94,
97
+ "h2_t": 95,
98
+ "a3_t": 96,
99
+ "b3_t": 97,
100
+ "c3_t": 98,
101
+ "d3_t": 99,
102
+ "e3_t": 100,
103
+ "f3_t": 101,
104
+ "g3_t": 102,
105
+ "h3_t": 103,
106
+ "a4_t": 104,
107
+ "b4_t": 105,
108
+ "c4_t": 106,
109
+ "d4_t": 107,
110
+ "e4_t": 108,
111
+ "f4_t": 109,
112
+ "g4_t": 110,
113
+ "h4_t": 111,
114
+ "a5_t": 112,
115
+ "b5_t": 113,
116
+ "c5_t": 114,
117
+ "d5_t": 115,
118
+ "e5_t": 116,
119
+ "f5_t": 117,
120
+ "g5_t": 118,
121
+ "h5_t": 119,
122
+ "a6_t": 120,
123
+ "b6_t": 121,
124
+ "c6_t": 122,
125
+ "d6_t": 123,
126
+ "e6_t": 124,
127
+ "f6_t": 125,
128
+ "g6_t": 126,
129
+ "h6_t": 127,
130
+ "a7_t": 128,
131
+ "b7_t": 129,
132
+ "c7_t": 130,
133
+ "d7_t": 131,
134
+ "e7_t": 132,
135
+ "f7_t": 133,
136
+ "g7_t": 134,
137
+ "h7_t": 135,
138
+ "a8_t": 136,
139
+ "b8_t": 137,
140
+ "c8_t": 138,
141
+ "d8_t": 139,
142
+ "e8_t": 140,
143
+ "f8_t": 141,
144
+ "g8_t": 142,
145
+ "h8_t": 143
146
+ }