neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev7/qwen2/Qwen/Qwen2.5-32B-Instruct/898176f767d85650b19b.json

{
  "_entry_class": "SingleModelCacheEntry",
  "_model_id": "Qwen/Qwen2.5-32B-Instruct",
  "_task": "text-generation",
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "hidden_act": "silu",
  "hidden_size": 5120,
  "initializer_range": 0.02,
  "intermediate_size": 27648,
  "max_position_embeddings": 32768,
  "max_window_layers": 70,
  "model_type": "qwen2",
  "neuron": {
    "_serialized_key": "HloNeuronConfig",
    "all_reduce_dtype": null,
    "allow_flash_attention": true,
    "attention_layout": "HSB",
    "attn_output_transposed": false,
    "auto_cast_type": "bf16",
    "batch_size": 1,
    "checkpoint_id": "Qwen/Qwen2.5-32B-Instruct",
    "checkpoint_revision": "5ede1c97bbab6ce5cda5812749b4c0bdf79b18dd",
    "collectives_layout": "HSB",
    "continuous_batching": false,
    "fuse_qkv": false,
    "group_query_attention": "shard-over-heads",
    "log_softmax_scores": false,
    "neuronxcc_version": "2.17.194.0+d312836f",
    "optimum_neuron_version": "0.2.0.dev7",
    "output_all_logits": false,
    "sequence_length": 4096,
    "tp_degree": 8
  },
  "num_attention_heads": 40,
  "num_hidden_layers": 64,
  "num_key_value_heads": 8,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": 131072,
  "tie_word_embeddings": false,
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 152064
}