optimum-neuron-cache
/
neuronxcc-2.14.227.0+2d4f85be
/0_REGISTRY
/0.0.25.dev0
/inference
/mistral
/mistralai
/Mistral-7B-Instruct-v0.3
/7493e5d5c6554ee91778.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": "fp16", "batch_size": 4, "checkpoint_id": "mistralai/Mistral-7B-Instruct-v0.3", "checkpoint_revision": "e0bc86c23ce5aae1db576c8cca6f06f1f73af2db", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 4, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "rms_norm_eps": 1e-05, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 32768} |