{ "architectures": [ "Qwen3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151645, "head_dim": 128, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 12288, "max_position_embeddings": 40960, "max_window_layers": 36, "model_type": "qwen3", "num_attention_heads": 32, "num_hidden_layers": 36, "num_key_value_heads": 8, "quantization_config": { "config_groups": { "group_0": { "input_activations": null, "output_activations": null, "targets": [ "re:.*gate_proj.*", "re:.*up_proj.*", "re:.*down_proj.*", "re:.*k_proj.*", "re:.*q_proj.*", "re:.*v_proj.*", "re:.*o_proj.*" ], "weights": { "actorder": null, "block_structure": null, "dynamic": false, "group_size": 128, "num_bits": 4, "observer": "minmax", "observer_kwargs": {}, "strategy": "group", "symmetric": true, "type": "int" }, "ignore": [ "score" ] } }, "format": "pack-quantized", "global_compression_ratio": null, "ignore": [ "lm_head", "score" ], "kv_cache_scheme": null, "quant_method": "compressed-tensors", "quantization_status": "compressed" }, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "float16", "transformers_version": "4.52.4", "use_cache": true, "use_sliding_window": false, "vocab_size": 151669, "classifier_from_token": [ "no", "yes" ], "is_original_qwen3_reranker": true, "_reranker_note": "This is a quantized reranker model. Load with vLLM using: --hf-overrides '{\"architectures\": [\"Qwen3ForSequenceClassification\"], \"classifier_from_token\": [\"no\", \"yes\"], \"is_original_qwen3_reranker\": true}'", "_quantized_from": "Qwen/Qwen3-Reranker-8B" }