| { | |
| "architectures": ["CustomGPT"], | |
| "model_type": "gpt", | |
| "vocab_size": 8192, | |
| "n_positions": 512, | |
| "n_embd": 512, | |
| "n_layer": 16, | |
| "n_head": 8, | |
| "n_inner": 2048, | |
| "activation": "gelu", | |
| "norm": "rmsnorm", | |
| "tie_word_embeddings": true, | |
| "attention": "causal-fused-qkv", | |
| "n_params": 54804992, | |
| "dtype": "float32", | |
| "note": "Custom GPT (not a transformers architecture). Load with model_loader.py. Weights in model.safetensors (99 tensors, weight-tied: tok.weight serves both embedding and output projection)." | |
| } | |