optimum-neuron-cache
/
neuronxcc-2.14.227.0+2d4f85be
/0_REGISTRY
/0.0.24.dev0
/inference
/llama
/defog
/sqlcoder-7b-2
/2a7f28749bf930679a90.json
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 11008, "max_position_embeddings": 16384, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "defog/sqlcoder-7b-2", "checkpoint_revision": "7e5b6f7981c0aa7d143f6bec6fa26625bdfcbe66", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 1000000, "tie_word_embeddings": false, "torch_dtype": "float16", "use_cache": true, "vocab_size": 32016} |