Chess Challenge submission by j0eyd

README.md

@@ -0,0 +1,26 @@
+---
+library_name: transformers
+tags:
+- chess
+- llm-course
+- chess-challenge
+license: mit
+---
+
+# square_chess
+
+Chess model submitted to the LLM Course Chess Challenge.
+
+## Submission Info
+
+- **Submitted by**: [j0eyd](https://huggingface.co/j0eyd)
+- **Parameters**: 869,120
+- **Organization**: LLM-course
+
+## Model Details
+
+- **Architecture**: Chess Transformer (GPT-style)
+- **Vocab size**: 72
+- **Embedding dim**: 128
+- **Layers**: 5
+- **Heads**: 4

config.json

@@ -0,0 +1,96 @@
+{
+  "architectures": [
+    "ChessForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "dropout": 0.05,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "id_to_token_text": [
+    "",
+    "",
+    "",
+    "",
+    "a1",
+    "b1",
+    "c1",
+    "d1",
+    "e1",
+    "f1",
+    "g1",
+    "h1",
+    "a2",
+    "b2",
+    "c2",
+    "d2",
+    "e2",
+    "f2",
+    "g2",
+    "h2",
+    "a3",
+    "b3",
+    "c3",
+    "d3",
+    "e3",
+    "f3",
+    "g3",
+    "h3",
+    "a4",
+    "b4",
+    "c4",
+    "d4",
+    "e4",
+    "f4",
+    "g4",
+    "h4",
+    "a5",
+    "b5",
+    "c5",
+    "d5",
+    "e5",
+    "f5",
+    "g5",
+    "h5",
+    "a6",
+    "b6",
+    "c6",
+    "d6",
+    "e6",
+    "f6",
+    "g6",
+    "h6",
+    "a7",
+    "b7",
+    "c7",
+    "d7",
+    "e7",
+    "f7",
+    "g7",
+    "h7",
+    "a8",
+    "b8",
+    "c8",
+    "d8",
+    "e8",
+    "f8",
+    "g8",
+    "h8",
+    "q",
+    "r",
+    "b",
+    "n"
+  ],
+  "layer_norm_epsilon": 1e-05,
+  "mask_invalid_moves": true,
+  "model_type": "chess_transformer",
+  "n_ctx": 256,
+  "n_embd": 128,
+  "n_head": 4,
+  "n_inner": 384,
+  "n_layer": 5,
+  "pad_token_id": 0,
+  "tie_weights": true,
+  "transformers_version": "4.57.5",
+  "unk_token_id": 3,
+  "vocab_size": 72
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6468430b31f2d9bbe65a648145f96929ea702a4a0d5dc9bb3f51caf079dfdbda
+size 3481904

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "[BOS]",
+  "eos_token": "[EOS]",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[BOS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[EOS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[BOS]",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "[EOS]",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "ChessSquaresTokenizer",
+  "unk_token": "[UNK]"
+}

vocab.json

@@ -0,0 +1 @@
+{"[PAD]": 0, "[BOS]": 1, "[EOS]": 2, "[UNK]": 3, "a1": 4, "b1": 5, "c1": 6, "d1": 7, "e1": 8, "f1": 9, "g1": 10, "h1": 11, "a2": 12, "b2": 13, "c2": 14, "d2": 15, "e2": 16, "f2": 17, "g2": 18, "h2": 19, "a3": 20, "b3": 21, "c3": 22, "d3": 23, "e3": 24, "f3": 25, "g3": 26, "h3": 27, "a4": 28, "b4": 29, "c4": 30, "d4": 31, "e4": 32, "f4": 33, "g4": 34, "h4": 35, "a5": 36, "b5": 37, "c5": 38, "d5": 39, "e5": 40, "f5": 41, "g5": 42, "h5": 43, "a6": 44, "b6": 45, "c6": 46, "d6": 47, "e6": 48, "f6": 49, "g6": 50, "h6": 51, "a7": 52, "b7": 53, "c7": 54, "d7": 55, "e7": 56, "f7": 57, "g7": 58, "h7": 59, "a8": 60, "b8": 61, "c8": 62, "d8": 63, "e8": 64, "f8": 65, "g8": 66, "h8": 67, "q": 68, "r": 69, "b": 70, "n": 71}