{ "architectures": ["GPT"], "vocab_size": 128, "n_layer": 4, "n_embd": 44, "n_head": 2, "block_size": 512, "rope_theta": 100000.0, "ffn": "gelu", "ffn_mult": 2.667, "tie_word_embeddings": true, "params": 100936, "params_note": "unique param count (tied head counted once); the safetensors file stores the head twice, so its raw numel sum is 106568" }