Upload Checkmate model

README.md

@@ -0,0 +1,39 @@
+---
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- chess
+- gpt_neox
+- pythia
+---
+
+# Checkmate-5M
+
+A tiny chess move model built for the [Chess LLM Arena](https://huggingface.co/spaces/mlabonne/chessllm).
+
+- **Architecture:** Pythia / GPT-NeoX (6 layers, hidden size 128, 4 heads), trained from scratch.
+- **Parameters:** 4.8M
+- **Tokenizer:** move-level chess tokenizer: one token per SAN move (without `+`/`#`), plus the
+  move-number prompt `1.` and single SAN characters. Every legal SAN move is a single token.
+- **Training:** the move-selection policy was optimized with reinforcement learning (policy
+  gradient) on millions of simulated games against the models at the top of the arena
+  leaderboard, then distilled into the network.
+- **Best used as White.**
+
+## Usage in the arena
+
+Type `DedeProGames/Checkmate-5M` as the **White** model in the arena and press *Fight!*.
+
+## Usage with transformers + outlines
+
+```python
+import chess, re
+import outlines.models as models
+from outlines import generate
+
+model = models.transformers("DedeProGames/Checkmate-5M")
+board = chess.Board()
+legal = "|".join(re.escape(re.sub(r"[+#]", "", board.san(m))) for m in board.legal_moves)
+print(generate.regex(model, legal)("1."))
+```

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 1,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 128,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 64,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "partial_rotary_factor": 0.25,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 14035
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.48.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8ab062edf361152ea8ec17b26f6332215458dcf56ea80d1b75b4eeacdf90df7
+size 19139888

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "extra_special_tokens": {},
+  "model_max_length": 64,
+  "pad_token": "<pad>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}