{ "_name_or_path": "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO", "architectures": [ "MixtralForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 32000, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 32768, "model_type": "mixtral", "neuron": { "auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO", "checkpoint_revision": "286ae6737d048ad1d965c2e830864df02db50f2f", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 24, "sequence_length": 4096, "task": "text-generation" }, "num_attention_heads": 32, "num_experts_per_tok": 2, "num_hidden_layers": 32, "num_key_value_heads": 8, "num_local_experts": 8, "output_router_logits": false, "rms_norm_eps": 1e-05, "rope_theta": 1000000.0, "router_aux_loss_coef": 0.02, "router_jitter_noise": 0.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.41.2", "use_cache": false, "vocab_size": 32002 }