config.json

{
  "adapter_dim": 512,
  "architectures": [
    "modeling_camelidae.LlamaForCausalLM"
  ],
  "auto_map": {
    "AutoConfig": "configuration_camelidae.CamelidaeConfig",
    "AutoModel": "modeling_camelidae.LlamaModel",
    "AutoModelForCausalLM": "modeling_camelidae.LlamaForCausalLM"
  },
  "bos_token_id": 1,
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 7168,
  "initializer_range": 0.02,
  "intermediate_size": 20480,
  "max_position_embeddings": 4096,
  "model_type": "camelidae",
  "moe_dtype": "bfloat16",
  "moe_scaling": 0.25,
  "num_attention_heads": 56,
  "num_experts": 8,
  "num_hidden_layers": 60,
  "num_key_value_heads": 8,
  "output_router_logits": false,
  "pad_token_id": 0,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 5000000.0,
  "tie_word_embeddings": false,
  "topk": 2,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.34.0.dev0",
  "use_cache": true,
  "vocab_size": 64000
}