CoolFace
Modelpublic

XingTuLab/BinSeek-Reranker

sourceHugging Facegpl-3.0updated 10mo agoView on Hugging Face
0likes29downloads
config.json72 linesDownload Raw Back to root
1{2  "architectures": [3    "Qwen3ForSequenceClassification"4  ],5  "attention_bias": false,6  "attention_dropout": 0.0,7  "dtype": "bfloat16",8  "eos_token_id": 151645,9  "head_dim": 128,10  "hidden_act": "silu",11  "hidden_size": 1024,12  "id2label": {13    "0": "LABEL_0"14  },15  "initializer_range": 0.02,16  "intermediate_size": 3072,17  "label2id": {18    "LABEL_0": 019  },20  "layer_types": [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    "full_attention",42    "full_attention",43    "full_attention",44    "full_attention",45    "full_attention",46    "full_attention",47    "full_attention",48    "full_attention"49  ],50  "max_position_embeddings": 40960,51  "max_window_layers": 28,52  "model_type": "qwen3",53  "num_attention_heads": 16,54  "num_hidden_layers": 28,55  "num_key_value_heads": 8,56  "pad_token": "<|endoftext|>",57  "pad_token_id": 151643,58  "rms_norm_eps": 1e-06,59  "rope_scaling": null,60  "rope_theta": 1000000,61  "sentence_transformers": {62    "activation_fn": "torch.nn.modules.activation.Sigmoid",63    "version": "5.1.2"64  },65  "sliding_window": null,66  "tie_word_embeddings": true,67  "transformers_version": "4.57.1",68  "use_cache": true,69  "use_sliding_window": false,70  "vocab_size": 15166971}72