Upload folder using huggingface_hub

README.md

@@ -1,3 +1,74 @@
-chessmodel
+# chesshacks_model
 
-2025-11-15 16:48:46
+NNUE (Efficiently Updatable Neural Network) chess evaluation model
+
+## Model Details
+
+- **Model type**: NNUE Chess Evaluation
+- **Architecture**: HalfKP feature representation
+- **Uploaded**: 2025-11-15 17:03:16
+
+## Architecture
+
+```
+Input: HalfKP features (40,960 dimensions per perspective)
+  ↓
+Feature Transformer: 40,960 → 256 (separate for white/black)
+  ↓
+ClippedReLU activation
+  ↓
+Concatenate: 256 + 256 → 512
+  ↓
+Hidden Layer 1: 512 → 32 + ClippedReLU
+  ↓
+Hidden Layer 2: 32 → 32 + ClippedReLU
+  ↓
+Output Layer: 32 → 1 (centipawn evaluation)
+```
+
+## Training Information
+
+- **Epoch**: 1
+- **Training Loss**: 3135323.2188
+- **Validation Loss**: 3236829.0000
+
+## Usage
+
+```python
+import torch
+from huggingface_hub import hf_hub_download
+import chess
+
+# Download and load model
+checkpoint_path = hf_hub_download(repo_id="chesshacks_model", filename="pytorch_model.bin")
+checkpoint = torch.load(checkpoint_path, map_location='cpu')
+
+# Load model config
+model_config = checkpoint['model_config']
+
+# Create model instance (you'll need the NNUEModel class)
+# from model import NNUEModel
+# model = NNUEModel(**model_config)
+# model.load_state_dict(checkpoint['model_state_dict'])
+# model.eval()
+
+# Evaluate a position
+# board = chess.Board()
+# score = model.evaluate_board(board)
+# print(f"Evaluation: {score:.2f} centipawns")
+```
+
+## Training Configuration
+
+- **batch_size**: 256
+- **learning_rate**: 0.001
+- **num_epochs**: 2
+- **optimizer**: adam
+- **loss_function**: mse
+- **hidden_size**: 256
+- **hidden2_size**: 32
+- **hidden3_size**: 32
+
+---
+
+*Model generated with NNUE training pipeline*

best_model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c725ea63f4d635ebdf7406ecd9fac0f5e09cbb874b3eab3a8cfce79d179a44d
+oid sha256:819f5299839f0432894e7a1620e4cb2c7baa85013cec1bef0418cc7b7df87ab6
 size 126054005

config.json

@@ -4,7 +4,7 @@
     "hidden_size": 256,
     "hidden2_size": 32,
     "hidden3_size": 32,
-    "feature_size": 4096000
+    "feature_size": 40960
   },
   "training_config": {
     "train_data_path": "data/train.jsonl",
@@ -22,7 +22,6 @@
     "train_val_split_ratio": 0.9,
     "checkpoint_dir": "checkpoints",
     "save_every_n_epochs": 10,
-    "save_best_only": true,
     "validate_every_n_epochs": 1,
     "device": "cpu",
     "optimizer": "adam",
@@ -59,7 +58,7 @@
     "resume_from": null,
     "hf_repo_id": "jleezhang/chesshacks_model",
     "hf_auto_upload": true,
-    "hf_upload_all_checkpoints": true,
+    "hf_upload_all_checkpoints": false,
     "hf_checkpoints_dir": null,
     "hf_model_name": null,
     "hf_model_description": null,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00e23ec8d1d48e8f206511caee1b87a0e220e6a7ff650d6057a02922bc7b9e35
+oid sha256:f3de791f85735ebaf380901683b410362c3e83683c67330dc66a6755860032d5
 size 42017825