{ "_name_or_path": "None", "architectures": [ "CustomMixtralForCausalLM" ], "attention_dropout": 0.0, "auto_map": { "AutoModelForCausalLM": "custom_mixtral.CustomMixtralForCausalLM" }, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 1024, "initializer_range": 0.02, "intermediate_size": 2400, "max_position_embeddings": 131072, "model_type": "mixtral", "num_attention_heads": 16, "num_experts_per_tok": 1, "num_hidden_layers": 24, "num_key_value_heads": 8, "num_local_experts": 2, "output_router_logits": true, "rms_norm_eps": 1e-05, "rope_theta": 10000.0, "router_aux_loss_coef": 0.01, "sliding_window": 1024, "tie_word_embeddings": false, "torch_dtype": "float16", "transformers_version": "4.39.1", "use_cache": true, "vocab_size": 32000 }