neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev0/granite/ibm-granite/granite-3.1-8b-instruct/9ecfc518ded6f3373fde.json

{
  "_entry_class": "SingleModelCacheEntry",
  "_model_id": "ibm-granite/granite-3.1-8b-instruct",
  "_task": "text-generation",
  "architectures": [
    "GraniteForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.1,
  "attention_multiplier": 0.0078125,
  "dtype": "bfloat16",
  "embedding_multiplier": 12.0,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 12800,
  "logits_scaling": 16.0,
  "max_position_embeddings": 131072,
  "mlp_bias": false,
  "model_type": "granite",
  "neuron": {
    "_serialized_key": "NxDNeuronConfig",
    "batch_size": 4,
    "capacity_factor": null,
    "checkpoint_id": "ibm-granite/granite-3.1-8b-instruct",
    "checkpoint_revision": "4009206d5fc95d2e65a7b7633e159d6e97e25d35",
    "continuous_batching": true,
    "ep_degree": 1,
    "fused_qkv": true,
    "glu_mlp": true,
    "local_ranks_size": 2,
    "max_batch_size": 4,
    "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": 2
  },
  "num_attention_heads": 32,
  "num_hidden_layers": 40,
  "num_key_value_heads": 8,
  "residual_multiplier": 0.22,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000000.0,
  "tie_word_embeddings": true,
  "use_cache": true,
  "vocab_size": 49155
}