neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev5/llama/lmsys/vicuna-7b-v1.5/9557e9f068806717bb5e.json

{
  "_entry_class": "SingleModelCacheEntry",
  "_model_id": "lmsys/vicuna-7b-v1.5",
  "_task": "text-generation",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_position_embeddings": 4096,
  "mlp_bias": false,
  "model_type": "llama",
  "neuron": {
    "_serialized_key": "NxDNeuronConfig",
    "batch_size": 1,
    "capacity_factor": null,
    "checkpoint_id": "lmsys/vicuna-7b-v1.5",
    "checkpoint_revision": "3321f76e3f527bd14065daf69dad9344000a201d",
    "continuous_batching": false,
    "enable_bucketing": false,
    "ep_degree": 1,
    "fused_qkv": true,
    "glu_mlp": true,
    "local_ranks_size": 2,
    "logical_nc_config": 1,
    "max_batch_size": 1,
    "max_context_length": 4096,
    "max_topk": 256,
    "n_active_tokens": 4096,
    "neuronxcc_version": "2.19.8089.0+8ab9f450",
    "on_device_sampling": true,
    "optimum_neuron_version": "0.3.1.dev5",
    "output_logits": false,
    "pp_degree": 1,
    "sequence_length": 4096,
    "speculation_length": 0,
    "start_rank_id": 0,
    "target": null,
    "torch_dtype": "float16",
    "tp_degree": 2
  },
  "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": 10000.0,
  "tie_word_embeddings": false,
  "use_cache": true,
  "vocab_size": 32000
}