config.json

{
  "architectures": ["SealGlazerLM"],
  "model_type": "sealglazer",
  "vocab_size": 8192,
  "hidden_size": 128,
  "num_hidden_layers": 4,
  "num_attention_heads": 4,
  "intermediate_size": 384,
  "max_position_embeddings": 256,
  "rms_norm_eps": 1e-6,
  "tie_word_embeddings": true,
  "dtype": "float32",
  "rope_theta": 10000.0,
  "num_parameters": 1901696,
  "notes": "From-scratch Llama-style causal LM (RMSNorm + RoPE + SwiGLU MLP + MHA). Custom architecture, not a standard transformers model_type; load with the provided load_sealglazer.py. Embeddings are tied (single tok.weight used for both input embedding and lm_head)."
}