{
  "_entry_class": "SingleModelCacheEntry",
  "_model_id": "deepseek-ai/DeepSeek-R1-Distill-Llama-8B",
  "_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": 14336,
  "max_position_embeddings": 131072,
  "mlp_bias": false,
  "model_type": "llama",
  "neuron": {
    "_serialized_key": "HloNeuronConfig",
    "all_reduce_dtype": null,
    "allow_flash_attention": true,
    "attention_layout": "BSH",
    "attn_output_transposed": false,
    "auto_cast_type": "bf16",
    "batch_size": 4,
    "checkpoint_id": "deepseek-ai/DeepSeek-R1-Distill-Llama-8B",
    "checkpoint_revision": "6a6f4aa4197940add57724a7707d069478df56b1",
    "collectives_layout": "HSB",
    "continuous_batching": true,
    "fuse_qkv": true,
    "group_query_attention": "shard-over-heads",
    "log_softmax_scores": false,
    "neuronxcc_version": "2.17.194.0+d312836f",
    "optimum_neuron_version": "0.2.0.dev5",
    "output_all_logits": false,
    "sequence_length": 4096,
    "tp_degree": 8
  },
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "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
}