config.json

{
  "architectures": [
    "AquilaDenseForCausalLM"
  ],
  "auto_map": {
    "AutoConfig": "configuration_aquiladense.AquilaDenseConfig",
    "AutoModelForCausalLM": "modeling_aquiladense.AquilaDenseForCausalLM"
  },
  "attention_dropout": 0.0,
  "bos_token_id": 151849,
  "eos_token_id": 151850,
  "hidden_act": "silu",
  "hidden_size": 5120,
  "initializer_range": 0.02,
  "intermediate_size": 17920,
  "rms_norm_eps": 1e-05,
  "max_position_embeddings": 4096,
  "model_type": "aquiladense",
  "num_attention_heads": 40,
  "num_hidden_layers": 40,
  "num_key_value_heads": 8,
  "pad_token_id": 151643,
  "pretraining_tp": 1,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.37.2",
  "_attn_implementation": "flash_attention_2",
  "use_cache": true,
  "vocab_size": 151851
}