CoolFace
Modelpublic

Proactive-Interactive-R1/Proactive-Interactive-R1-Math-7B-Pro

sourceHugging Faceupdated 9mo agoView on Hugging Face
0likes11downloads
config.json61 linesDownload Raw Back to root
1{2  "architectures": [3    "Qwen2ForCausalLM"4  ],5  "attention_dropout": 0.0,6  "bos_token_id": 151646,7  "eos_token_id": 151643,8  "hidden_act": "silu",9  "hidden_size": 3584,10  "initializer_range": 0.02,11  "intermediate_size": 18944,12  "layer_types": [13    "full_attention",14    "full_attention",15    "full_attention",16    "full_attention",17    "full_attention",18    "full_attention",19    "full_attention",20    "full_attention",21    "full_attention",22    "full_attention",23    "full_attention",24    "full_attention",25    "full_attention",26    "full_attention",27    "full_attention",28    "full_attention",29    "full_attention",30    "full_attention",31    "full_attention",32    "full_attention",33    "full_attention",34    "full_attention",35    "full_attention",36    "full_attention",37    "full_attention",38    "full_attention",39    "full_attention",40    "full_attention"41  ],42  "max_position_embeddings": 131072,43  "max_window_layers": 28,44  "model_type": "qwen2",45  "num_attention_heads": 28,46  "num_hidden_layers": 28,47  "num_key_value_heads": 4,48  "pad_token_id": 151643,49  "rms_norm_eps": 1e-06,50  "rope_scaling": null,51  "rope_theta": 10000,52  "sliding_window": null,53  "tie_word_embeddings": false,54  "torch_dtype": "bfloat16",55  "transformers_version": "4.51.1",56  "use_cache": false,57  "use_mrope": false,58  "use_sliding_window": false,59  "vocab_size": 15206460}61