{
  "model_type": "axon",
  "architectures": [
    "AxonForCausalLM"
  ],
  "hidden_size": 1024,
  "intermediate_size": 2560,
  "num_hidden_layers": 30,
  "num_attention_heads": 8,
  "num_key_value_heads": 4,
  "vocab_size": 49152,
  "max_position_embeddings": 2048,
  "rope_theta": 10000.0,
  "logit_softcap": 30.0,
  "hidden_act": "relu2",
  "rms_norm_eps": 1e-05,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "custom",
  "training_tokens": 8499888128,
  "best_train_loss": 4.409422159194946,
  "training_step": 64849
}