neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev0/llama/meta-llama/Llama-3.3-70B-Instruct/f7df94fad99b911aa4b3.json

{
  "_entry_class": "SingleModelCacheEntry",
  "_model_id": "meta-llama/Llama-3.3-70B-Instruct",
  "_task": "text-generation",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "dtype": "bfloat16",
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 8192,
  "initializer_range": 0.02,
  "intermediate_size": 28672,
  "max_position_embeddings": 131072,
  "mlp_bias": false,
  "model_type": "llama",
  "neuron": {
    "_serialized_key": "NxDNeuronConfig",
    "batch_size": 8,
    "capacity_factor": null,
    "checkpoint_id": "meta-llama/Llama-3.3-70B-Instruct",
    "checkpoint_revision": "6f6073b423013f6a7d4d9f39144961bfbfbc386b",
    "continuous_batching": true,
    "ep_degree": 1,
    "fused_qkv": true,
    "glu_mlp": true,
    "local_ranks_size": 32,
    "max_batch_size": 8,
    "max_context_length": 4096,
    "max_topk": 256,
    "n_active_tokens": 4096,
    "neuronxcc_version": "2.21.33363.0+82129205",
    "on_device_sampling": true,
    "optimum_neuron_version": "0.4.4.dev0",
    "output_logits": false,
    "pp_degree": 1,
    "sequence_length": 4096,
    "speculation_length": 0,
    "start_rank_id": 0,
    "target": "trn1",
    "torch_dtype": "bfloat16",
    "tp_degree": 32
  },
  "num_attention_heads": 64,
  "num_hidden_layers": 80,
  "num_key_value_heads": 8,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "factor": 8.0,
    "high_freq_factor": 4.0,
    "low_freq_factor": 1.0,
    "original_max_position_embeddings": 8192,
    "rope_type": "llama3"
  },
  "rope_theta": 500000.0,
  "tie_word_embeddings": false,
  "use_cache": true,
  "vocab_size": 128256
}