{
  "_name_or_path": "/ckpts/nemotron/nemotron3-8b-hf-new",
  "architectures": [
    "NemotronForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 2,
  "eos_token_id": 3,
  "head_dim": 128,
  "hidden_act": "relu2",
  "hidden_size": 4096,
  "initializer_range": 0.01,
  "intermediate_size": 16384,
  "max_position_embeddings": 4096,
  "mlp_bias": false,
  "model_type": "nemotron",
  "norm_eps": 1e-05,
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "partial_rotary_factor": 0.5,
  "rope_theta": 10000,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.44.0",
  "use_cache": true,
  "vocab_size": 256000
}