Chess Challenge submission by swdo
Browse files- README.md +26 -0
- config.json +20 -0
- model.safetensors +3 -0
- special_tokens_map.json +6 -0
- tokenizer_config.json +44 -0
- vocab.json +90 -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 |
+
# chess_4
|
| 11 |
+
|
| 12 |
+
Chess model submitted to the LLM Course Chess Challenge.
|
| 13 |
+
|
| 14 |
+
## Submission Info
|
| 15 |
+
|
| 16 |
+
- **Submitted by**: [swdo](https://huggingface.co/swdo)
|
| 17 |
+
- **Parameters**: 705,792
|
| 18 |
+
- **Organization**: LLM-course
|
| 19 |
+
|
| 20 |
+
## Model Details
|
| 21 |
+
|
| 22 |
+
- **Architecture**: Chess Transformer (GPT-style)
|
| 23 |
+
- **Vocab size**: 88
|
| 24 |
+
- **Embedding dim**: 128
|
| 25 |
+
- **Layers**: 4
|
| 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": 4,
|
| 16 |
+
"pad_token_id": 0,
|
| 17 |
+
"tie_weights": true,
|
| 18 |
+
"transformers_version": "4.57.3",
|
| 19 |
+
"vocab_size": 88
|
| 20 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72aec51248ed61411d2a7d13e7e0e2ca86d6515998cefa92dff605a179731979
|
| 3 |
+
size 2827568
|
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 +1,90 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 0,
|
| 3 |
+
"[BOS]": 1,
|
| 4 |
+
"[EOS]": 2,
|
| 5 |
+
"[UNK]": 3,
|
| 6 |
+
"[W]": 4,
|
| 7 |
+
"[B]": 5,
|
| 8 |
+
"P": 6,
|
| 9 |
+
"N": 7,
|
| 10 |
+
"B": 8,
|
| 11 |
+
"R": 9,
|
| 12 |
+
"Q": 10,
|
| 13 |
+
"K": 11,
|
| 14 |
+
"a1": 12,
|
| 15 |
+
"a2": 13,
|
| 16 |
+
"a3": 14,
|
| 17 |
+
"a4": 15,
|
| 18 |
+
"a5": 16,
|
| 19 |
+
"a6": 17,
|
| 20 |
+
"a7": 18,
|
| 21 |
+
"a8": 19,
|
| 22 |
+
"b1": 20,
|
| 23 |
+
"b2": 21,
|
| 24 |
+
"b3": 22,
|
| 25 |
+
"b4": 23,
|
| 26 |
+
"b5": 24,
|
| 27 |
+
"b6": 25,
|
| 28 |
+
"b7": 26,
|
| 29 |
+
"b8": 27,
|
| 30 |
+
"c1": 28,
|
| 31 |
+
"c2": 29,
|
| 32 |
+
"c3": 30,
|
| 33 |
+
"c4": 31,
|
| 34 |
+
"c5": 32,
|
| 35 |
+
"c6": 33,
|
| 36 |
+
"c7": 34,
|
| 37 |
+
"c8": 35,
|
| 38 |
+
"d1": 36,
|
| 39 |
+
"d2": 37,
|
| 40 |
+
"d3": 38,
|
| 41 |
+
"d4": 39,
|
| 42 |
+
"d5": 40,
|
| 43 |
+
"d6": 41,
|
| 44 |
+
"d7": 42,
|
| 45 |
+
"d8": 43,
|
| 46 |
+
"e1": 44,
|
| 47 |
+
"e2": 45,
|
| 48 |
+
"e3": 46,
|
| 49 |
+
"e4": 47,
|
| 50 |
+
"e5": 48,
|
| 51 |
+
"e6": 49,
|
| 52 |
+
"e7": 50,
|
| 53 |
+
"e8": 51,
|
| 54 |
+
"f1": 52,
|
| 55 |
+
"f2": 53,
|
| 56 |
+
"f3": 54,
|
| 57 |
+
"f4": 55,
|
| 58 |
+
"f5": 56,
|
| 59 |
+
"f6": 57,
|
| 60 |
+
"f7": 58,
|
| 61 |
+
"f8": 59,
|
| 62 |
+
"g1": 60,
|
| 63 |
+
"g2": 61,
|
| 64 |
+
"g3": 62,
|
| 65 |
+
"g4": 63,
|
| 66 |
+
"g5": 64,
|
| 67 |
+
"g6": 65,
|
| 68 |
+
"g7": 66,
|
| 69 |
+
"g8": 67,
|
| 70 |
+
"h1": 68,
|
| 71 |
+
"h2": 69,
|
| 72 |
+
"h3": 70,
|
| 73 |
+
"h4": 71,
|
| 74 |
+
"h5": 72,
|
| 75 |
+
"h6": 73,
|
| 76 |
+
"h7": 74,
|
| 77 |
+
"h8": 75,
|
| 78 |
+
"x": 76,
|
| 79 |
+
"+": 77,
|
| 80 |
+
"#": 78,
|
| 81 |
+
"+*": 79,
|
| 82 |
+
"=Q": 80,
|
| 83 |
+
"=R": 81,
|
| 84 |
+
"=B": 82,
|
| 85 |
+
"=N": 83,
|
| 86 |
+
"O-O": 84,
|
| 87 |
+
"O-O-O": 85,
|
| 88 |
+
"o": 86,
|
| 89 |
+
"O": 87
|
| 90 |
+
}
|