TuringGame/Qwen3-0.6B-classifier

1{2  "architectures": [3    "Qwen3ForSequenceClassification"4  ],5  "attention_bias": false,6  "attention_dropout": 0.0,7  "bos_token_id": 151643,8  "eos_token_id": 151645,9  "head_dim": 128,10  "hidden_act": "silu",11  "hidden_size": 1024,12  "id2label": {13    "0": "HUMAN",14    "1": "AI"15  },16  "initializer_range": 0.02,17  "intermediate_size": 3072,18  "label2id": {19    "AI": 1,20    "HUMAN": 021  },22  "layer_types": [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    "full_attention",50    "full_attention"51  ],52  "max_position_embeddings": 40960,53  "max_window_layers": 28,54  "model_type": "qwen3",55  "num_attention_heads": 16,56  "num_hidden_layers": 28,57  "num_key_value_heads": 8,58  "pad_token_id": 151645,59  "problem_type": "single_label_classification",60  "rms_norm_eps": 1e-06,61  "rope_scaling": null,62  "rope_theta": 1000000,63  "sliding_window": null,64  "tie_word_embeddings": true,65  "torch_dtype": "float32",66  "transformers_version": "4.53.3",67  "use_cache": true,68  "use_sliding_window": false,69  "vocab_size": 15193670}71