{
  "architectures": [
    "FlashAttentionForCausalLM"
  ],
  "model_type": "flash_attention_lm",
  "vocab_size": 50257,
  "hidden_size": 512,
  "num_hidden_layers": 8,
  "num_attention_heads": 8,
  "max_position_embeddings": 512,
  "hidden_dropout_prob": 0.1,
  "use_flash_attention": true,
  "gradient_checkpointing": false,
  "torch_dtype": "float32",
  "transformers_version": "4.40.0"
}