{ "_name_or_path": "meta-llama/Meta-Llama-3-8B", "adapter_dim": 64, "architectures": [ "LlamaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "auto_map": { "AutoConfig": "configuration_camelidae.CamelidaeConfig", "AutoModelForCausalLM": "modeling_camelidae.LlamaForCausalLM" }, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "model_type": "llama", "moe_dtype": "bfloat16", "moe_scaling": 0.25, "num_attention_heads": 32, "num_clusters": 7, "num_experts": 8, "num_hidden_layers": 32, "num_key_value_heads": 8, "output_router_logits": false, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "topk": 2, "torch_dtype": "bfloat16", "transformers_version": "4.34.0.dev0", "use_cache": true, "vocab_size": 128256 }