{
  "_name_or_path": "/mnt/data/ckpt/pcl/qwen_full_lr5e-6_beta0-03_rew01_actor-loss-dro_kl-reg-unbiased1e-2_plot-weights_critic",
  "architectures": [
    "LLMForSequenceRegression"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151643,
  "hidden_act": "silu",
  "hidden_size": 1536,
  "initializer_range": 0.02,
  "intermediate_size": 8960,
  "max_position_embeddings": 4096,
  "max_window_layers": 21,
  "model_type": "qwen2",
  "normalize_reward": false,
  "num_attention_heads": 12,
  "num_hidden_layers": 28,
  "num_key_value_heads": 2,
  "rms_norm_eps": 1e-06,
  "rope_theta": 10000,
  "sliding_window": 4096,
  "tie_word_embeddings": true,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.41.2",
  "use_cache": true,
  "use_mrope": false,
  "use_sliding_window": false,
  "vocab_size": 151936
}