Upload BT4 Chess model

README.md

@@ -0,0 +1,57 @@
+---
+license: mit
+tags:
+- chess
+- reinforcement-learning
+- game-ai
+- pytorch
+library_name: transformers
+---
+
+# BT4 Chess Model
+
+This is a BT4 (Board Transformer 4) model for chess move prediction and position evaluation.
+
+## Model Description
+
+The BT4 model is a transformer-based architecture designed for chess gameplay. It can:
+- Predict the next best move given a chess position (FEN)
+- Evaluate chess positions
+- Generate move probabilities
+
+## Usage
+
+```python
+from HFChessRL import BT4Model, BT4Config
+import torch
+
+# Load the model
+model = BT4Model.from_pretrained("Maxlegrec/ChessBot")
+
+# Example usage
+fen = "rnbqkbnr/pppppppp/8/8/8/8/PPPPPPPP/RNBQKBNR w KQkq - 0 1"
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model = model.to(device)
+
+# Get the best move
+move = model.get_move_from_fen_no_thinking(fen, T=0.1, device=device)
+print(f"Predicted move: {move}")
+```
+
+## Model Architecture
+
+- **Transformer layers**: 10
+- **Hidden size**: 512
+- **Feed-forward size**: 736
+- **Attention heads**: 8
+- **Vocabulary size**: 1929 (chess moves)
+
+## Training Data
+
+This model was trained on chess game data to learn optimal move selection and position evaluation.
+
+## Limitations
+
+- The model works best with standard chess positions
+- Performance may vary with unusual or rare positions
+- Requires GPU for optimal inference speed

config.json

@@ -0,0 +1,14 @@
+{
+  "architectures": [
+    "BT4Model"
+  ],
+  "d_ff": 736,
+  "d_model": 512,
+  "max_position_embeddings": 64,
+  "model_type": "bt4",
+  "num_heads": 8,
+  "num_layers": 10,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.1",
+  "vocab_size": 1929
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bde7187dc7db04da9762fe80fe1926454c45f5711e386786f34de55fa4d218e
+size 122277600