optimum-neuron-cache
/
neuronxcc-2.13.66.0+6dfecc895
/0_REGISTRY
/0.0.23
/inference
/mistral
/HuggingFaceH4
/zephyr-7b-beta
/8822798add0906fb14ad.json
{"architectures": ["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": "mistral", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "HuggingFaceH4/zephyr-7b-beta", "checkpoint_revision": "b70e0c9a2d9e14bd1e812d3c398e5f313e93b473", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pad_token_id": 2, "rms_norm_eps": 1e-05, "rope_theta": 10000.0, "sliding_window": 4096, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 32000} |