{
  "_entry_class": "SingleModelCacheEntry",
  "_model_id": "hf-internal-testing/tiny-random-GraniteForCausalLM",
  "_task": "text-generation",
  "architectures": [
    "GraniteForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "attention_multiplier": 1.0,
  "embedding_multiplier": 1.0,
  "hidden_act": "silu",
  "hidden_size": 32,
  "initializer_range": 0.02,
  "intermediate_size": 64,
  "logits_scaling": 1.0,
  "max_position_embeddings": 2048,
  "mlp_bias": false,
  "model_type": "granite",
  "neuron": {
    "_serialized_key": "HloNeuronConfig",
    "all_reduce_dtype": null,
    "allow_flash_attention": true,
    "attention_layout": "HSB",
    "attn_output_transposed": false,
    "auto_cast_type": "fp16",
    "batch_size": 2,
    "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM",
    "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5",
    "collectives_layout": "HSB",
    "continuous_batching": true,
    "fuse_qkv": true,
    "group_query_attention": null,
    "log_softmax_scores": false,
    "neuronxcc_version": "2.17.194.0+d312836f",
    "optimum_neuron_version": "0.2.0.dev7",
    "output_all_logits": false,
    "sequence_length": 100,
    "tp_degree": 2
  },
  "num_attention_heads": 4,
  "num_hidden_layers": 2,
  "num_key_value_heads": 4,
  "residual_multiplier": 1.0,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "use_cache": true,
  "vocab_size": 49152
}