{ "architectures": [ "Qwen3_5ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "dtype": "bfloat16", "eos_token_id": 2, "head_dim": 64, "hidden_act": "silu", "hidden_size": 640, "initializer_range": 0.02, "intermediate_size": 2560, "layer_types": [ "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention" ], "linear_conv_kernel_dim": 4, "linear_key_head_dim": 128, "linear_num_key_heads": 2, "linear_num_value_heads": 4, "linear_value_head_dim": 128, "max_position_embeddings": 2048, "model_type": "qwen3_5_text", "num_attention_heads": 8, "num_hidden_layers": 8, "num_key_value_heads": 2, "pad_token_id": null, "partial_rotary_factor": 0.25, "rms_norm_eps": 1e-06, "rope_parameters": { "partial_rotary_factor": 0.25, "rope_theta": 10000.0, "rope_type": "default" }, "tie_word_embeddings": true, "transformers_version": "5.13.1", "use_cache": true, "vocab_size": 16000 }