neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5.dev1/43f30d107729db6b760b2a90833f43ca44f68e6468ef64e131f71e2fa9f5b23f/b76d86cc7c31e0e29c99.json

{
  "_entry_class": "SingleModelCacheEntry",
  "_model_id": "openai/gpt-oss-20b",
  "_task": "text-generation",
  "architectures": [
    "GptOssForCausalLM"
  ],
  "attention_bias": true,
  "attention_dropout": 0.0,
  "dtype": "bfloat16",
  "experts_per_token": 4,
  "head_dim": 64,
  "hidden_act": "silu",
  "hidden_size": 2880,
  "initial_context_length": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 2880,
  "layer_types": [
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention"
  ],
  "max_position_embeddings": 131072,
  "model_type": "gpt_oss",
  "neuron": {
    "_serialized_key": "NxDNeuronConfig",
    "batch_size": 1,
    "capacity_factor": null,
    "checkpoint_id": "openai/gpt-oss-20b",
    "checkpoint_revision": "6cee5e81ee83917806bbde320786a8fb61efebee",
    "continuous_batching": false,
    "ep_degree": 1,
    "fused_qkv": true,
    "glu_mlp": true,
    "local_ranks_size": 8,
    "max_batch_size": 1,
    "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": "0.4.5.dev1",
    "output_logits": false,
    "pp_degree": 1,
    "sequence_length": 4096,
    "speculation_length": 0,
    "start_rank_id": 0,
    "target": "trn1",
    "torch_dtype": "bfloat16",
    "tp_degree": 8
  },
  "num_attention_heads": 64,
  "num_experts_per_tok": 4,
  "num_hidden_layers": 24,
  "num_key_value_heads": 8,
  "num_local_experts": 32,
  "output_router_logits": false,
  "quantization_config": {
    "modules_to_not_convert": [
      "model.layers.*.self_attn",
      "model.layers.*.mlp.router",
      "model.embed_tokens",
      "lm_head"
    ],
    "quant_method": "mxfp4"
  },
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "beta_fast": 32.0,
    "beta_slow": 1.0,
    "factor": 32.0,
    "original_max_position_embeddings": 4096,
    "rope_type": "yarn",
    "truncate": false
  },
  "rope_theta": 150000,
  "router_aux_loss_coef": 0.9,
  "sliding_window": 128,
  "swiglu_limit": 7.0,
  "tie_word_embeddings": false,
  "use_cache": true,
  "vocab_size": 201088
}