{ "adapter_dim": 512, "adapter_dropout": 0.0, "architectures": [ "modeling_sparsetral.MistralForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 32768, "model_type": "sparsetral", "moe_dtype": "bfloat16", "moe_scaling": 1, "num_attention_heads": 32, "num_experts": 16, "num_hidden_layers": 32, "num_key_value_heads": 8, "output_router_logits": false, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_theta": 1000000.0, "router_aux_loss_coef": 0.01, "sliding_window": null, "tie_word_embeddings": false, "topk": 4, "torch_dtype": "bfloat16", "transformers_version": "4.37.2", "use_cache": true, "vocab_size": 32000, "auto_map": { "AutoConfig": "configuration_sparsetral.SparsetralConfig", "AutoModel": "modeling_sparsetral.MistralModel", "AutoModelForCausalLM": "modeling_sparsetral.MistralForCausalLM" } }