{
  "architectures": [
    "AttnOnlyForCausalLM"
  ],
  "attn_pdrop": 0.0,
  "embd_pdrop": 0.0,
  "hidden_size": 768,
  "layer_norm": false,
  "layer_norm_epsilon": 1e-05,
  "max_position_embeddings": 1024,
  "model_type": "attn_only",
  "num_attention_heads": 12,
  "num_hidden_layers": 2,
  "resid_pdrop": 0.0,
  "special_pos_embed": true,
  "torch_dtype": "float32",
  "transformers_version": "4.55.4",
  "use_cache": true,
  "vocab_size": 50257
}