trl-internal-testing/tiny-Qwen3ForSequenceClassification

1{2  "architectures": [3    "Qwen3ForSequenceClassification"4  ],5  "attention_bias": false,6  "attention_dropout": 0.0,7  "bos_token_id": 151643,8  "dtype": "bfloat16",9  "eos_token_id": 151645,10  "head_dim": 128,11  "hidden_act": "silu",12  "hidden_size": 16,13  "id2label": {14    "0": "LABEL_0"15  },16  "initializer_range": 0.02,17  "intermediate_size": 32,18  "label2id": {19    "LABEL_0": 020  },21  "layer_types": [22    "full_attention",23    "full_attention"24  ],25  "max_position_embeddings": 40960,26  "max_window_layers": 36,27  "model_type": "qwen3",28  "num_attention_heads": 4,29  "num_hidden_layers": 2,30  "num_key_value_heads": 2,31  "rms_norm_eps": 1e-06,32  "rope_scaling": null,33  "rope_theta": 1000000,34  "sliding_window": null,35  "tie_word_embeddings": true,36  "transformers_version": "4.57.3",37  "use_cache": true,38  "use_sliding_window": false,39  "vocab_size": 15193640}41