{ "_name_or_path": "Crystalcareai/Qwen-1.5-8x7B", "architectures": [ "MixtralForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": null, "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 11008, "max_position_embeddings": 32768, "max_window_layers": 28, "model_type": "mixtral", "num_attention_heads": 32, "num_experts_per_tok": 2, "num_hidden_layers": 32, "num_key_value_heads": 32, "num_local_experts": 8, "output_router_logits": true, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "router_aux_loss_coef": 0.001, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.38.0.dev0", "use_cache": false, "use_sliding_window": false, "vocab_size": 151936 }