{ "_name_or_path": "p1atdev/dart-v2-mixtral-160m-sft-8", "architectures": [ "MixtralForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 0, "eos_token_id": 1, "hidden_act": "silu", "hidden_size": 768, "initializer_range": 0.02, "intermediate_size": 3072, "max_position_embeddings": 1024, "model_type": "mixtral", "num_attention_heads": 8, "num_experts_per_tok": 2, "num_hidden_layers": 4, "num_key_value_heads": 1, "num_local_experts": 4, "output_router_logits": false, "pad_token_id": 2, "rms_norm_eps": 1e-05, "rope_theta": 1000.0, "router_aux_loss_coef": 0.02, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.38.2", "use_cache": true, "vocab_size": 30649 }