{
  "_name_or_path": "/share/project/zhipengchen/RLHF/ckpt/GRPO-ds_qwen_1.5B-iter1_steps60-iter2_steps60-iter3_steps60-DATA_0124-tbs_512-rbs_128-sample_8-kl_0.001-warmup_0.0-ep_10000-plr_2e6-glen_20k-reward_v0/_actor/steps30",
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "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": 131072,
  "max_window_layers": 21,
  "model_type": "qwen2",
  "num_attention_heads": 12,
  "num_hidden_layers": 28,
  "num_key_value_heads": 2,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 10000,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.46.3",
  "use_cache": true,
  "use_mrope": false,
  "use_sliding_window": false,
  "vocab_size": 151936
}