{ "add_cross_attention": false, "architectures": [ "Qwen3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 151643, "chunk_size_feed_forward": 0, "diversity_penalty": 0.0, "do_sample": false, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": [ 151643, 151645 ], "head_dim": 128, "hidden_act": "silu", "hidden_size": 2048, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 6144, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 65536, "min_length": 0, "model_type": "qwen3", "no_repeat_ngram_size": 0, "num_attention_heads": 16, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 28, "num_key_value_heads": 8, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": 151643, "pruned_heads": {}, "quantization": { "group_size": 64, "bits": 4, "mode": "affine" }, "quantization_config": { "group_size": 64, "bits": 4, "mode": "affine" }, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "rms_norm_eps": 1e-06, "rope_scaling": { "interleaved": true, "mrope_interleaved": true, "mrope_section": [ 24, 20, 20 ], "rope_type": "default", "type": "default" }, "rope_theta": 1000000, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": true, "top_k": 50, "top_p": 1.0, "torch_dtype": "bfloat16", "torchscript": false, "typical_p": 1.0, "use_bfloat16": false, "use_cache": true, "vocab_size": 151936 }