| { |
| "architectures": [ |
| "Qwen2ForRewardModel" |
| ], |
| "auto_map": { |
| "AutoConfig": "configuration_qwen2_rm.Qwen2RMConfig", |
| "AutoModel": "modeling_qwen2_rm.Qwen2ForRewardModel" |
| }, |
| "attention_dropout": 0.0, |
| "hidden_act": "silu", |
| "hidden_size": 3584, |
| "initializer_range": 0.02, |
| "intermediate_size": 18944, |
| "max_position_embeddings": 32768, |
| "max_window_layers": 28, |
| "model_type": "qwen2", |
| "num_attention_heads": 28, |
| "num_hidden_layers": 28, |
| "num_key_value_heads": 4, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 1000000.0, |
| "sliding_window": null, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.46.2", |
| "use_cache": true, |
| "use_sliding_window": false, |
| "vocab_size": 152064 |
| } |
|
|
