neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/mixtral/mistralai/Mixtral-8x7B-Instruct-v0.1/064296b30b0f10af57d2.json

{"architectures": ["MixtralForCausalLM"], "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": "mixtral", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "mistralai/Mixtral-8x7B-Instruct-v0.1", "checkpoint_revision": "41bd4c9e7e4fb318ca40e721131d4933966c2cc1", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "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", "use_cache": true, "vocab_size": 32000}