config.json

{
  "_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151643,
  "hidden_act": "silu",
  "hidden_size": 5120,
  "initializer_range": 0.02,
  "intermediate_size": 27648,
  "max_position_embeddings": 131072,
  "max_window_layers": 64,
  "model_type": "qwen2",
  "neuron": {
    "auto_cast_type": "bf16",
    "batch_size": 1,
    "checkpoint_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
    "checkpoint_revision": "711ad2ea6aa40cfca18895e8aca02ab92df1a746",
    "compiler_type": "neuronx-cc",
    "compiler_version": "2.16.372.0+4a9b2326",
    "num_cores": 12,
    "sequence_length": 32768,
    "task": "text-generation"
  },
  "num_attention_heads": 40,
  "num_hidden_layers": 64,
  "num_key_value_heads": 8,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.48.3",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 152064
}