{ "architectures": [ "QTSplusQwen2_5_VLTextForCausalLM" ], "auto_map": { "AutoConfig": "configuration_qts_plus_qwen2_5_vl.QTSplusQwen2_5_VL_CausalLM_Config", "AutoModelForCausalLM": "modeling_qts_plus_qwen2_5_vl.QTSplusQwen2_5_VLTextForCausalLM", "AutoProcessor": "processing_qts_plus_qwen2_5_vl.QTSplusQwen2_5_VLProcessor" }, "vision_tower": "qwen2_5_vl_vision", "enable_qts_plus": true, "qts_plus_n_heads": 28, "qts_plus_tau_s": 0.5, "qts_plus_nmax": 25600, "qts_plus_rho_min": 0.05, "qts_plus_rho_max": 0.5, "qts_plus_block_dropout": 0.0, "qts_plus_reencode": true, "qts_plus_scoring_layers": 1, "qts_plus_reencode_layers": 2, "project_text_if_needed": false, "freeze_qts_scoring_layers": false, "lambda_t": 0, "lambda_m": 0, "lambda_s": 0, "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151645, "vision_start_token_id": 151652, "vision_end_token_id": 151653, "vision_token_id": 151654, "image_token_id": 151655, "video_token_id": 151656, "hidden_act": "silu", "hidden_size": 3584, "initializer_range": 0.02, "intermediate_size": 18944, "max_position_embeddings": 128000, "max_window_layers": 28, "model_type": "qts_plus_qwen2_5_vl_causal_lm", "num_attention_heads": 28, "num_hidden_layers": 28, "num_key_value_heads": 4, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.57.1", "use_cache": true, "use_sliding_window": false, "vision_config": { "depth": 32, "hidden_act": "silu", "hidden_size": 1280, "intermediate_size": 3420, "num_heads": 16, "in_chans": 3, "out_hidden_size": 3584, "patch_size": 14, "spatial_merge_size": 2, "spatial_patch_size": 14, "window_size": 112, "fullatt_block_indexes": [ 7, 15, 23, 31 ], "tokens_per_second": 2, "temporal_patch_size": 2 }, "rope_scaling": { "type": "mrope", "mrope_section": [ 16, 24, 24 ] }, "vocab_size": 152064 }