| { |
| "architectures": [ |
| "Qwen3ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 151643, |
| "dtype": "bfloat16", |
| "eos_token_id": 151645, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 4096, |
| "initializer_range": 0.02, |
| "intermediate_size": 12288, |
| "layer_types": [ |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention" |
| ], |
| "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": { |
| "format": "nvfp4-pack-quantized", |
| "input_activations": { |
| "actorder": null, |
| "block_structure": null, |
| "dynamic": "local", |
| "group_size": 16, |
| "num_bits": 4, |
| "observer": "minmax", |
| "observer_kwargs": {}, |
| "strategy": "tensor_group", |
| "symmetric": true, |
| "type": "float" |
| }, |
| "output_activations": null, |
| "targets": [ |
| "Linear" |
| ], |
| "weights": { |
| "actorder": null, |
| "block_structure": null, |
| "dynamic": false, |
| "group_size": 16, |
| "num_bits": 4, |
| "observer": "minmax", |
| "observer_kwargs": {}, |
| "strategy": "tensor_group", |
| "symmetric": true, |
| "type": "float" |
| } |
| } |
| }, |
| "format": "nvfp4-pack-quantized", |
| "global_compression_ratio": null, |
| "ignore": [ |
| "model.layers.0.self_attn.q_proj", |
| "model.layers.0.self_attn.k_proj", |
| "model.layers.0.self_attn.v_proj", |
| "model.layers.0.self_attn.o_proj", |
| "model.layers.0.mlp.gate_proj", |
| "model.layers.0.mlp.up_proj", |
| "model.layers.0.mlp.down_proj", |
| "model.layers.1.self_attn.q_proj", |
| "model.layers.1.self_attn.k_proj", |
| "model.layers.1.self_attn.v_proj", |
| "model.layers.1.self_attn.o_proj", |
| "model.layers.2.self_attn.q_proj", |
| "model.layers.2.self_attn.k_proj", |
| "model.layers.2.self_attn.v_proj", |
| "model.layers.2.self_attn.o_proj", |
| "model.layers.3.self_attn.q_proj", |
| "model.layers.3.self_attn.k_proj", |
| "model.layers.3.self_attn.v_proj", |
| "model.layers.3.self_attn.o_proj", |
| "model.layers.4.self_attn.q_proj", |
| "model.layers.4.self_attn.k_proj", |
| "model.layers.4.self_attn.v_proj", |
| "model.layers.4.self_attn.o_proj", |
| "model.layers.5.self_attn.q_proj", |
| "model.layers.5.self_attn.k_proj", |
| "model.layers.5.self_attn.v_proj", |
| "model.layers.5.self_attn.o_proj", |
| "model.layers.6.self_attn.q_proj", |
| "model.layers.6.self_attn.k_proj", |
| "model.layers.6.self_attn.v_proj", |
| "model.layers.6.self_attn.o_proj", |
| "model.layers.7.self_attn.q_proj", |
| "model.layers.7.self_attn.k_proj", |
| "model.layers.7.self_attn.v_proj", |
| "model.layers.7.self_attn.o_proj", |
| "model.layers.8.self_attn.q_proj", |
| "model.layers.8.self_attn.k_proj", |
| "model.layers.8.self_attn.v_proj", |
| "model.layers.8.self_attn.o_proj", |
| "model.layers.8.mlp.gate_proj", |
| "model.layers.8.mlp.up_proj", |
| "model.layers.8.mlp.down_proj", |
| "model.layers.9.self_attn.q_proj", |
| "model.layers.9.self_attn.k_proj", |
| "model.layers.9.self_attn.v_proj", |
| "model.layers.9.self_attn.o_proj", |
| "model.layers.9.mlp.gate_proj", |
| "model.layers.9.mlp.up_proj", |
| "model.layers.9.mlp.down_proj", |
| "model.layers.10.self_attn.q_proj", |
| "model.layers.10.self_attn.k_proj", |
| "model.layers.10.self_attn.v_proj", |
| "model.layers.10.self_attn.o_proj", |
| "model.layers.11.self_attn.q_proj", |
| "model.layers.11.self_attn.k_proj", |
| "model.layers.11.self_attn.v_proj", |
| "model.layers.11.self_attn.o_proj", |
| "model.layers.12.self_attn.q_proj", |
| "model.layers.12.self_attn.k_proj", |
| "model.layers.12.self_attn.v_proj", |
| "model.layers.12.self_attn.o_proj", |
| "model.layers.13.self_attn.q_proj", |
| "model.layers.13.self_attn.k_proj", |
| "model.layers.13.self_attn.v_proj", |
| "model.layers.13.self_attn.o_proj", |
| "model.layers.14.self_attn.q_proj", |
| "model.layers.14.self_attn.k_proj", |
| "model.layers.14.self_attn.v_proj", |
| "model.layers.14.self_attn.o_proj", |
| "model.layers.15.self_attn.q_proj", |
| "model.layers.15.self_attn.k_proj", |
| "model.layers.15.self_attn.v_proj", |
| "model.layers.15.self_attn.o_proj", |
| "model.layers.16.self_attn.q_proj", |
| "model.layers.16.self_attn.k_proj", |
| "model.layers.16.self_attn.v_proj", |
| "model.layers.16.self_attn.o_proj", |
| "model.layers.17.self_attn.q_proj", |
| "model.layers.17.self_attn.k_proj", |
| "model.layers.17.self_attn.v_proj", |
| "model.layers.17.self_attn.o_proj", |
| "model.layers.17.mlp.gate_proj", |
| "model.layers.17.mlp.up_proj", |
| "model.layers.17.mlp.down_proj", |
| "model.layers.18.self_attn.q_proj", |
| "model.layers.18.self_attn.k_proj", |
| "model.layers.18.self_attn.v_proj", |
| "model.layers.18.self_attn.o_proj", |
| "model.layers.18.mlp.gate_proj", |
| "model.layers.18.mlp.up_proj", |
| "model.layers.18.mlp.down_proj", |
| "model.layers.19.self_attn.q_proj", |
| "model.layers.19.self_attn.k_proj", |
| "model.layers.19.self_attn.v_proj", |
| "model.layers.19.self_attn.o_proj", |
| "model.layers.20.self_attn.q_proj", |
| "model.layers.20.self_attn.k_proj", |
| "model.layers.20.self_attn.v_proj", |
| "model.layers.20.self_attn.o_proj", |
| "model.layers.21.self_attn.q_proj", |
| "model.layers.21.self_attn.k_proj", |
| "model.layers.21.self_attn.v_proj", |
| "model.layers.21.self_attn.o_proj", |
| "model.layers.22.self_attn.q_proj", |
| "model.layers.22.self_attn.k_proj", |
| "model.layers.22.self_attn.v_proj", |
| "model.layers.22.self_attn.o_proj", |
| "model.layers.23.self_attn.q_proj", |
| "model.layers.23.self_attn.k_proj", |
| "model.layers.23.self_attn.v_proj", |
| "model.layers.23.self_attn.o_proj", |
| "model.layers.24.self_attn.q_proj", |
| "model.layers.24.self_attn.k_proj", |
| "model.layers.24.self_attn.v_proj", |
| "model.layers.24.self_attn.o_proj", |
| "model.layers.25.self_attn.q_proj", |
| "model.layers.25.self_attn.k_proj", |
| "model.layers.25.self_attn.v_proj", |
| "model.layers.25.self_attn.o_proj", |
| "model.layers.26.self_attn.q_proj", |
| "model.layers.26.self_attn.k_proj", |
| "model.layers.26.self_attn.v_proj", |
| "model.layers.26.self_attn.o_proj", |
| "model.layers.26.mlp.gate_proj", |
| "model.layers.26.mlp.up_proj", |
| "model.layers.26.mlp.down_proj", |
| "model.layers.27.self_attn.q_proj", |
| "model.layers.27.self_attn.k_proj", |
| "model.layers.27.self_attn.v_proj", |
| "model.layers.27.self_attn.o_proj", |
| "model.layers.27.mlp.gate_proj", |
| "model.layers.27.mlp.up_proj", |
| "model.layers.27.mlp.down_proj", |
| "model.layers.28.self_attn.q_proj", |
| "model.layers.28.self_attn.k_proj", |
| "model.layers.28.self_attn.v_proj", |
| "model.layers.28.self_attn.o_proj", |
| "model.layers.29.self_attn.q_proj", |
| "model.layers.29.self_attn.k_proj", |
| "model.layers.29.self_attn.v_proj", |
| "model.layers.29.self_attn.o_proj", |
| "model.layers.30.self_attn.q_proj", |
| "model.layers.30.self_attn.k_proj", |
| "model.layers.30.self_attn.v_proj", |
| "model.layers.30.self_attn.o_proj", |
| "model.layers.31.self_attn.q_proj", |
| "model.layers.31.self_attn.k_proj", |
| "model.layers.31.self_attn.v_proj", |
| "model.layers.31.self_attn.o_proj", |
| "model.layers.32.self_attn.q_proj", |
| "model.layers.32.self_attn.k_proj", |
| "model.layers.32.self_attn.v_proj", |
| "model.layers.32.self_attn.o_proj", |
| "model.layers.33.self_attn.q_proj", |
| "model.layers.33.self_attn.k_proj", |
| "model.layers.33.self_attn.v_proj", |
| "model.layers.33.self_attn.o_proj", |
| "model.layers.34.self_attn.q_proj", |
| "model.layers.34.self_attn.k_proj", |
| "model.layers.34.self_attn.v_proj", |
| "model.layers.34.self_attn.o_proj", |
| "model.layers.35.self_attn.q_proj", |
| "model.layers.35.self_attn.k_proj", |
| "model.layers.35.self_attn.v_proj", |
| "model.layers.35.self_attn.o_proj", |
| "lm_head", |
| "re:.*self_attn.*", |
| "re:.*layers\\.(0|8|9|17|18|26|27)\\.mlp.*" |
| ], |
| "kv_cache_scheme": null, |
| "quant_method": "compressed-tensors", |
| "quantization_status": "compressed", |
| "sparsity_config": {}, |
| "transform_config": {}, |
| "version": "0.12.2" |
| }, |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": null, |
| "rope_theta": 1000000, |
| "sliding_window": null, |
| "tie_word_embeddings": false, |
| "transformers_version": "4.57.1", |
| "use_cache": true, |
| "use_sliding_window": false, |
| "vocab_size": 151936 |
| } |
