| { |
| "architectures": [ |
| "Qwen2ForProcessRewardModel" |
| ], |
| "attention_dropout": 0.0, |
| "auto_map": { |
| "AutoConfig": "configuration_qwen2_rm.Qwen2RMConfig", |
| "AutoModel": "modeling_qwen2_rm.Qwen2ForProcessRewardModel", |
| "AutoModelForSequenceClassification": "modeling_qwen2_rm.Qwen2ForProcessRewardModel", |
| "AutoModelForTokenClassification": "modeling_qwen2_rm.Qwen2ForProcessRewardModel" |
| }, |
| "dtype": "bfloat16", |
| "eos_token_id": 151645, |
| "hidden_act": "silu", |
| "hidden_size": 3584, |
| "initializer_range": 0.02, |
| "intermediate_size": 18944, |
| "layer_types": [ |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention" |
| ], |
| "max_position_embeddings": 4096, |
| "max_window_layers": 28, |
| "model_type": "qwen2", |
| "num_attention_heads": 28, |
| "num_hidden_layers": 28, |
| "num_key_value_heads": 4, |
| "pad_token_id": 151643, |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": null, |
| "rope_theta": 10000.0, |
| "sliding_window": null, |
| "tie_word_embeddings": false, |
| "transformers_version": "4.57.6", |
| "use_cache": false, |
| "use_sliding_window": false, |
| "vocab_size": 152064, |
| "torch_dtype": "bfloat16", |
| "num_labels": 2, |
| "problem_type": "single_label_classification" |
| } |
|
|
