{ "_name_or_path": "models--SakuraLLM--Sakura-14B-Qwen2.5-v1.0", "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 5120, "initializer_range": 0.02, "intermediate_size": 13824, "max_position_embeddings": 32768, "max_window_layers": 70, "model_type": "qwen2", "num_attention_heads": 40, "num_hidden_layers": 48, "num_key_value_heads": 8, "quantization_config": { "config_groups": { "group_0": { "input_activations": { "actorder": null, "block_structure": null, "dynamic": true, "group_size": null, "num_bits": 8, "observer": null, "observer_kwargs": {}, "strategy": "token", "symmetric": true, "type": "int" }, "output_activations": null, "targets": [ "Linear" ], "weights": { "actorder": null, "block_structure": null, "dynamic": false, "group_size": null, "num_bits": 8, "observer": "minmax", "observer_kwargs": {}, "strategy": "channel", "symmetric": true, "type": "int" } } }, "format": "int-quantized", "global_compression_ratio": 1.4614890884279443, "ignore": [ "lm_head" ], "kv_cache_scheme": null, "quant_method": "compressed-tensors", "quantization_status": "compressed", "sparsity_config": { "format": "dense", "global_sparsity": 0.053354781474161325, "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.v_proj", "model.layers.1.self_attn.o_proj", "model.layers.1.mlp.down_proj", "model.layers.2.self_attn.v_proj", "model.layers.2.self_attn.o_proj", "model.layers.2.mlp.up_proj", "model.layers.2.mlp.down_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.3.mlp.up_proj", "model.layers.3.mlp.down_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.4.mlp.gate_proj", "model.layers.4.mlp.up_proj", "model.layers.4.mlp.down_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.5.mlp.gate_proj", "model.layers.5.mlp.up_proj", "model.layers.5.mlp.down_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.6.mlp.gate_proj", "model.layers.6.mlp.up_proj", "model.layers.6.mlp.down_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.7.mlp.gate_proj", "model.layers.7.mlp.up_proj", "model.layers.7.mlp.down_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.10.mlp.gate_proj", "model.layers.10.mlp.up_proj", "model.layers.10.mlp.down_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.11.mlp.gate_proj", "model.layers.11.mlp.up_proj", "model.layers.11.mlp.down_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.12.mlp.gate_proj", "model.layers.12.mlp.up_proj", "model.layers.12.mlp.down_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.13.mlp.gate_proj", "model.layers.13.mlp.up_proj", "model.layers.13.mlp.down_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.14.mlp.gate_proj", "model.layers.14.mlp.up_proj", "model.layers.14.mlp.down_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.15.mlp.gate_proj", "model.layers.15.mlp.up_proj", "model.layers.15.mlp.down_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.16.mlp.gate_proj", "model.layers.16.mlp.up_proj", "model.layers.16.mlp.down_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.19.mlp.gate_proj", "model.layers.19.mlp.up_proj", "model.layers.19.mlp.down_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.20.mlp.gate_proj", "model.layers.20.mlp.up_proj", "model.layers.20.mlp.down_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.21.mlp.gate_proj", "model.layers.21.mlp.up_proj", "model.layers.21.mlp.down_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.22.mlp.gate_proj", "model.layers.22.mlp.up_proj", "model.layers.22.mlp.down_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.23.mlp.gate_proj", "model.layers.23.mlp.up_proj", "model.layers.23.mlp.down_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.24.mlp.gate_proj", "model.layers.24.mlp.up_proj", "model.layers.24.mlp.down_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.25.mlp.gate_proj", "model.layers.25.mlp.up_proj", "model.layers.25.mlp.down_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.28.mlp.gate_proj", "model.layers.28.mlp.up_proj", "model.layers.28.mlp.down_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.29.mlp.gate_proj", "model.layers.29.mlp.up_proj", "model.layers.29.mlp.down_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.30.mlp.gate_proj", "model.layers.30.mlp.up_proj", "model.layers.30.mlp.down_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.31.mlp.gate_proj", "model.layers.31.mlp.up_proj", "model.layers.31.mlp.down_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.32.mlp.gate_proj", "model.layers.32.mlp.up_proj", "model.layers.32.mlp.down_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.33.mlp.gate_proj", "model.layers.33.mlp.up_proj", "model.layers.33.mlp.down_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.34.mlp.gate_proj", "model.layers.34.mlp.up_proj", "model.layers.34.mlp.down_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", "model.layers.35.mlp.gate_proj", "model.layers.35.mlp.up_proj", "model.layers.35.mlp.down_proj", "model.layers.36.self_attn.q_proj", "model.layers.36.self_attn.k_proj", "model.layers.36.self_attn.v_proj", "model.layers.36.self_attn.o_proj", "model.layers.36.mlp.gate_proj", "model.layers.36.mlp.up_proj", "model.layers.36.mlp.down_proj", "model.layers.37.self_attn.q_proj", "model.layers.37.self_attn.k_proj", "model.layers.37.self_attn.v_proj", "model.layers.37.self_attn.o_proj", "model.layers.37.mlp.gate_proj", "model.layers.37.mlp.up_proj", "model.layers.37.mlp.down_proj", "model.layers.38.self_attn.q_proj", "model.layers.38.self_attn.k_proj", "model.layers.38.self_attn.v_proj", "model.layers.38.self_attn.o_proj", "model.layers.38.mlp.gate_proj", "model.layers.38.mlp.up_proj", "model.layers.38.mlp.down_proj", "model.layers.39.self_attn.q_proj", "model.layers.39.self_attn.k_proj", "model.layers.39.self_attn.v_proj", "model.layers.39.self_attn.o_proj", "model.layers.39.mlp.gate_proj", "model.layers.39.mlp.up_proj", "model.layers.39.mlp.down_proj", "model.layers.40.self_attn.q_proj", "model.layers.40.self_attn.k_proj", "model.layers.40.self_attn.v_proj", "model.layers.40.self_attn.o_proj", "model.layers.40.mlp.gate_proj", "model.layers.40.mlp.up_proj", "model.layers.40.mlp.down_proj", "model.layers.41.self_attn.q_proj", "model.layers.41.self_attn.k_proj", "model.layers.41.self_attn.v_proj", "model.layers.41.self_attn.o_proj", "model.layers.41.mlp.gate_proj", "model.layers.41.mlp.up_proj", "model.layers.41.mlp.down_proj", "model.layers.42.self_attn.q_proj", "model.layers.42.self_attn.k_proj", "model.layers.42.self_attn.v_proj", "model.layers.42.self_attn.o_proj", "model.layers.42.mlp.gate_proj", "model.layers.42.mlp.up_proj", "model.layers.42.mlp.down_proj", "model.layers.43.self_attn.q_proj", "model.layers.43.self_attn.k_proj", "model.layers.43.self_attn.v_proj", "model.layers.43.self_attn.o_proj", "model.layers.43.mlp.gate_proj", "model.layers.43.mlp.up_proj", "model.layers.43.mlp.down_proj", "model.layers.44.self_attn.q_proj", "model.layers.44.self_attn.k_proj", "model.layers.44.self_attn.v_proj", "model.layers.44.self_attn.o_proj", "model.layers.44.mlp.gate_proj", "model.layers.44.mlp.up_proj", "model.layers.44.mlp.down_proj", "model.layers.45.self_attn.q_proj", "model.layers.45.self_attn.k_proj", "model.layers.45.self_attn.v_proj", "model.layers.45.self_attn.o_proj", "model.layers.45.mlp.gate_proj", "model.layers.45.mlp.up_proj", "model.layers.45.mlp.down_proj", "model.layers.46.self_attn.q_proj", "model.layers.46.self_attn.k_proj", "model.layers.46.self_attn.v_proj", "model.layers.46.self_attn.o_proj", "model.layers.46.mlp.gate_proj", "model.layers.46.mlp.up_proj", "model.layers.46.mlp.down_proj", "model.layers.47.self_attn.q_proj", "model.layers.47.self_attn.k_proj", "model.layers.47.self_attn.v_proj", "model.layers.47.self_attn.o_proj", "model.layers.47.mlp.gate_proj", "model.layers.47.mlp.up_proj", "model.layers.47.mlp.down_proj", "lm_head" ], "registry_requires_subclass": false, "sparsity_structure": "unstructured", "targets": [ "model.layers.1.self_attn.q_proj", "model.layers.1.self_attn.k_proj", "model.layers.1.mlp.gate_proj", "model.layers.1.mlp.up_proj", "model.layers.2.self_attn.q_proj", "model.layers.2.self_attn.k_proj", "model.layers.2.mlp.gate_proj", "model.layers.3.mlp.gate_proj" ] } }, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "float16", "transformers_version": "4.46.3", "use_cache": true, "use_sliding_window": false, "vocab_size": 152064 }