{
  "_name_or_path": "/home/ry21/robust_rm/reward_models_unified_merge/GRM-Gemma-2B-sftreg_GRM-gemma-2b_baseline_80Kdata_length3000_fulltrain_lr5e-6_5e-06_cpt100",
  "architectures": [
    "GemmaForSequenceClassification"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoModel": "Ray2333/GRM-Gemma-2B-sftreg--model.AutoModelForCausalLMWithValueHead",
    "AutoModelForSequenceClassification": "Ray2333/GRM-Gemma-2B-sftreg--model.AutoModelForCausalLMWithValueHead"
  },
  "bos_token_id": 2,
  "eos_token_id": 1,
  "head_dim": 256,
  "hidden_act": "gelu",
  "hidden_activation": "gelu_pytorch_tanh",
  "hidden_size": 2048,
  "id2label": {
    "0": "LABEL_0"
  },
  "initializer_range": 0.02,
  "intermediate_size": 16384,
  "label2id": {
    "LABEL_0": 0
  },
  "max_position_embeddings": 8192,
  "model_type": "gemma",
  "num_attention_heads": 8,
  "num_hidden_layers": 18,
  "num_key_value_heads": 1,
  "pad_token_id": 1,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "torch_dtype": "float16",
  "transformers_version": "4.44.2",
  "use_cache": true,
  "vhead_layer_type": "mlp",
  "vhead_num_layers": 1,
  "vhead_num_neurons": 1024,
  "vocab_size": 256000
}