| { |
| "architectures": [ |
| "Qwen3ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 151643, |
| "dtype": "float16", |
| "eos_token_id": 151645, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 2560, |
| "initializer_range": 0.02, |
| "intermediate_size": 9728, |
| "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, |
| "pad_token_id": null, |
| "quantization_config": { |
| "actorder": false, |
| "bits": 4, |
| "checkpoint_format": "gptq", |
| "desc_act": false, |
| "fp32_had": false, |
| "group_size": 32, |
| "groupsize": 32, |
| "modules_in_block_to_quantize": [ |
| "model.layers.0.mlp.down_proj", |
| "model.layers.0.mlp.gate_proj", |
| "model.layers.0.mlp.up_proj", |
| "model.layers.0.self_attn.k_proj", |
| "model.layers.0.self_attn.o_proj", |
| "model.layers.0.self_attn.q_proj", |
| "model.layers.0.self_attn.v_proj", |
| "model.layers.1.mlp.down_proj", |
| "model.layers.1.mlp.gate_proj", |
| "model.layers.1.mlp.up_proj", |
| "model.layers.1.self_attn.k_proj", |
| "model.layers.1.self_attn.o_proj", |
| "model.layers.1.self_attn.q_proj", |
| "model.layers.1.self_attn.v_proj", |
| "model.layers.10.mlp.down_proj", |
| "model.layers.10.mlp.gate_proj", |
| "model.layers.10.mlp.up_proj", |
| "model.layers.10.self_attn.k_proj", |
| "model.layers.10.self_attn.o_proj", |
| "model.layers.10.self_attn.q_proj", |
| "model.layers.10.self_attn.v_proj", |
| "model.layers.11.mlp.down_proj", |
| "model.layers.11.mlp.gate_proj", |
| "model.layers.11.mlp.up_proj", |
| "model.layers.11.self_attn.k_proj", |
| "model.layers.11.self_attn.o_proj", |
| "model.layers.11.self_attn.q_proj", |
| "model.layers.11.self_attn.v_proj", |
| "model.layers.12.mlp.down_proj", |
| "model.layers.12.mlp.gate_proj", |
| "model.layers.12.mlp.up_proj", |
| "model.layers.12.self_attn.k_proj", |
| "model.layers.12.self_attn.o_proj", |
| "model.layers.12.self_attn.q_proj", |
| "model.layers.12.self_attn.v_proj", |
| "model.layers.13.mlp.down_proj", |
| "model.layers.13.mlp.gate_proj", |
| "model.layers.13.mlp.up_proj", |
| "model.layers.13.self_attn.k_proj", |
| "model.layers.13.self_attn.o_proj", |
| "model.layers.13.self_attn.q_proj", |
| "model.layers.13.self_attn.v_proj", |
| "model.layers.14.mlp.down_proj", |
| "model.layers.14.mlp.gate_proj", |
| "model.layers.14.mlp.up_proj", |
| "model.layers.14.self_attn.k_proj", |
| "model.layers.14.self_attn.o_proj", |
| "model.layers.14.self_attn.q_proj", |
| "model.layers.14.self_attn.v_proj", |
| "model.layers.15.mlp.down_proj", |
| "model.layers.15.mlp.gate_proj", |
| "model.layers.15.mlp.up_proj", |
| "model.layers.15.self_attn.k_proj", |
| "model.layers.15.self_attn.o_proj", |
| "model.layers.15.self_attn.q_proj", |
| "model.layers.15.self_attn.v_proj", |
| "model.layers.16.mlp.down_proj", |
| "model.layers.16.mlp.gate_proj", |
| "model.layers.16.mlp.up_proj", |
| "model.layers.16.self_attn.k_proj", |
| "model.layers.16.self_attn.o_proj", |
| "model.layers.16.self_attn.q_proj", |
| "model.layers.16.self_attn.v_proj", |
| "model.layers.17.mlp.down_proj", |
| "model.layers.17.mlp.gate_proj", |
| "model.layers.17.mlp.up_proj", |
| "model.layers.17.self_attn.k_proj", |
| "model.layers.17.self_attn.o_proj", |
| "model.layers.17.self_attn.q_proj", |
| "model.layers.17.self_attn.v_proj", |
| "model.layers.18.mlp.down_proj", |
| "model.layers.18.mlp.gate_proj", |
| "model.layers.18.mlp.up_proj", |
| "model.layers.18.self_attn.k_proj", |
| "model.layers.18.self_attn.o_proj", |
| "model.layers.18.self_attn.q_proj", |
| "model.layers.18.self_attn.v_proj", |
| "model.layers.19.mlp.down_proj", |
| "model.layers.19.mlp.gate_proj", |
| "model.layers.19.mlp.up_proj", |
| "model.layers.19.self_attn.k_proj", |
| "model.layers.19.self_attn.o_proj", |
| "model.layers.19.self_attn.q_proj", |
| "model.layers.19.self_attn.v_proj", |
| "model.layers.2.mlp.down_proj", |
| "model.layers.2.mlp.gate_proj", |
| "model.layers.2.mlp.up_proj", |
| "model.layers.2.self_attn.k_proj", |
| "model.layers.2.self_attn.o_proj", |
| "model.layers.2.self_attn.q_proj", |
| "model.layers.2.self_attn.v_proj", |
| "model.layers.20.mlp.down_proj", |
| "model.layers.20.mlp.gate_proj", |
| "model.layers.20.mlp.up_proj", |
| "model.layers.20.self_attn.k_proj", |
| "model.layers.20.self_attn.o_proj", |
| "model.layers.20.self_attn.q_proj", |
| "model.layers.20.self_attn.v_proj", |
| "model.layers.21.mlp.down_proj", |
| "model.layers.21.mlp.gate_proj", |
| "model.layers.21.mlp.up_proj", |
| "model.layers.21.self_attn.k_proj", |
| "model.layers.21.self_attn.o_proj", |
| "model.layers.21.self_attn.q_proj", |
| "model.layers.21.self_attn.v_proj", |
| "model.layers.22.mlp.down_proj", |
| "model.layers.22.mlp.gate_proj", |
| "model.layers.22.mlp.up_proj", |
| "model.layers.22.self_attn.k_proj", |
| "model.layers.22.self_attn.o_proj", |
| "model.layers.22.self_attn.q_proj", |
| "model.layers.22.self_attn.v_proj", |
| "model.layers.23.mlp.down_proj", |
| "model.layers.23.mlp.gate_proj", |
| "model.layers.23.mlp.up_proj", |
| "model.layers.23.self_attn.k_proj", |
| "model.layers.23.self_attn.o_proj", |
| "model.layers.23.self_attn.q_proj", |
| "model.layers.23.self_attn.v_proj", |
| "model.layers.24.mlp.down_proj", |
| "model.layers.24.mlp.gate_proj", |
| "model.layers.24.mlp.up_proj", |
| "model.layers.24.self_attn.k_proj", |
| "model.layers.24.self_attn.o_proj", |
| "model.layers.24.self_attn.q_proj", |
| "model.layers.24.self_attn.v_proj", |
| "model.layers.25.mlp.down_proj", |
| "model.layers.25.mlp.gate_proj", |
| "model.layers.25.mlp.up_proj", |
| "model.layers.25.self_attn.k_proj", |
| "model.layers.25.self_attn.o_proj", |
| "model.layers.25.self_attn.q_proj", |
| "model.layers.25.self_attn.v_proj", |
| "model.layers.26.mlp.down_proj", |
| "model.layers.26.mlp.gate_proj", |
| "model.layers.26.mlp.up_proj", |
| "model.layers.26.self_attn.k_proj", |
| "model.layers.26.self_attn.o_proj", |
| "model.layers.26.self_attn.q_proj", |
| "model.layers.26.self_attn.v_proj", |
| "model.layers.27.mlp.down_proj", |
| "model.layers.27.mlp.gate_proj", |
| "model.layers.27.mlp.up_proj", |
| "model.layers.27.self_attn.k_proj", |
| "model.layers.27.self_attn.o_proj", |
| "model.layers.27.self_attn.q_proj", |
| "model.layers.27.self_attn.v_proj", |
| "model.layers.28.mlp.down_proj", |
| "model.layers.28.mlp.gate_proj", |
| "model.layers.28.mlp.up_proj", |
| "model.layers.28.self_attn.k_proj", |
| "model.layers.28.self_attn.o_proj", |
| "model.layers.28.self_attn.q_proj", |
| "model.layers.28.self_attn.v_proj", |
| "model.layers.29.mlp.down_proj", |
| "model.layers.29.mlp.gate_proj", |
| "model.layers.29.mlp.up_proj", |
| "model.layers.29.self_attn.k_proj", |
| "model.layers.29.self_attn.o_proj", |
| "model.layers.29.self_attn.q_proj", |
| "model.layers.29.self_attn.v_proj", |
| "model.layers.3.mlp.down_proj", |
| "model.layers.3.mlp.gate_proj", |
| "model.layers.3.mlp.up_proj", |
| "model.layers.3.self_attn.k_proj", |
| "model.layers.3.self_attn.o_proj", |
| "model.layers.3.self_attn.q_proj", |
| "model.layers.3.self_attn.v_proj", |
| "model.layers.30.mlp.down_proj", |
| "model.layers.30.mlp.gate_proj", |
| "model.layers.30.mlp.up_proj", |
| "model.layers.30.self_attn.k_proj", |
| "model.layers.30.self_attn.o_proj", |
| "model.layers.30.self_attn.q_proj", |
| "model.layers.30.self_attn.v_proj", |
| "model.layers.31.mlp.down_proj", |
| "model.layers.31.mlp.gate_proj", |
| "model.layers.31.mlp.up_proj", |
| "model.layers.31.self_attn.k_proj", |
| "model.layers.31.self_attn.o_proj", |
| "model.layers.31.self_attn.q_proj", |
| "model.layers.31.self_attn.v_proj", |
| "model.layers.32.mlp.down_proj", |
| "model.layers.32.mlp.gate_proj", |
| "model.layers.32.mlp.up_proj", |
| "model.layers.32.self_attn.k_proj", |
| "model.layers.32.self_attn.o_proj", |
| "model.layers.32.self_attn.q_proj", |
| "model.layers.32.self_attn.v_proj", |
| "model.layers.33.mlp.down_proj", |
| "model.layers.33.mlp.gate_proj", |
| "model.layers.33.mlp.up_proj", |
| "model.layers.33.self_attn.k_proj", |
| "model.layers.33.self_attn.o_proj", |
| "model.layers.33.self_attn.q_proj", |
| "model.layers.33.self_attn.v_proj", |
| "model.layers.34.mlp.down_proj", |
| "model.layers.34.mlp.gate_proj", |
| "model.layers.34.mlp.up_proj", |
| "model.layers.34.self_attn.k_proj", |
| "model.layers.34.self_attn.o_proj", |
| "model.layers.34.self_attn.q_proj", |
| "model.layers.34.self_attn.v_proj", |
| "model.layers.35.mlp.down_proj", |
| "model.layers.35.mlp.gate_proj", |
| "model.layers.35.mlp.up_proj", |
| "model.layers.35.self_attn.k_proj", |
| "model.layers.35.self_attn.o_proj", |
| "model.layers.35.self_attn.q_proj", |
| "model.layers.35.self_attn.v_proj", |
| "model.layers.4.mlp.down_proj", |
| "model.layers.4.mlp.gate_proj", |
| "model.layers.4.mlp.up_proj", |
| "model.layers.4.self_attn.k_proj", |
| "model.layers.4.self_attn.o_proj", |
| "model.layers.4.self_attn.q_proj", |
| "model.layers.4.self_attn.v_proj", |
| "model.layers.5.mlp.down_proj", |
| "model.layers.5.mlp.gate_proj", |
| "model.layers.5.mlp.up_proj", |
| "model.layers.5.self_attn.k_proj", |
| "model.layers.5.self_attn.o_proj", |
| "model.layers.5.self_attn.q_proj", |
| "model.layers.5.self_attn.v_proj", |
| "model.layers.6.mlp.down_proj", |
| "model.layers.6.mlp.gate_proj", |
| "model.layers.6.mlp.up_proj", |
| "model.layers.6.self_attn.k_proj", |
| "model.layers.6.self_attn.o_proj", |
| "model.layers.6.self_attn.q_proj", |
| "model.layers.6.self_attn.v_proj", |
| "model.layers.7.mlp.down_proj", |
| "model.layers.7.mlp.gate_proj", |
| "model.layers.7.mlp.up_proj", |
| "model.layers.7.self_attn.k_proj", |
| "model.layers.7.self_attn.o_proj", |
| "model.layers.7.self_attn.q_proj", |
| "model.layers.7.self_attn.v_proj", |
| "model.layers.8.mlp.down_proj", |
| "model.layers.8.mlp.gate_proj", |
| "model.layers.8.mlp.up_proj", |
| "model.layers.8.self_attn.k_proj", |
| "model.layers.8.self_attn.o_proj", |
| "model.layers.8.self_attn.q_proj", |
| "model.layers.8.self_attn.v_proj", |
| "model.layers.9.mlp.down_proj", |
| "model.layers.9.mlp.gate_proj", |
| "model.layers.9.mlp.up_proj", |
| "model.layers.9.self_attn.k_proj", |
| "model.layers.9.self_attn.o_proj", |
| "model.layers.9.self_attn.q_proj", |
| "model.layers.9.self_attn.v_proj" |
| ], |
| "quant_method": "gptq", |
| "quantization_bits": [ |
| { |
| "mlp.down_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.gate_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.up_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.k_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.o_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.q_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.v_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| } |
| }, |
| { |
| "mlp.down_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.gate_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.up_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.k_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.o_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.q_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.v_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| } |
| }, |
| { |
| "mlp.down_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.gate_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.up_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.k_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.o_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.q_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.v_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| } |
| }, |
| { |
| "mlp.down_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.gate_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.up_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.k_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.o_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.q_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.v_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| } |
| }, |
| { |
| "mlp.down_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.gate_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.up_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.k_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.o_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.q_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.v_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| } |
| }, |
| { |
| "mlp.down_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.gate_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.up_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.k_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.o_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.q_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.v_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| } |
| }, |
| { |
| "mlp.down_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.gate_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.up_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.k_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.o_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.q_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.v_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| } |
| }, |
| { |
| "mlp.down_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.gate_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.up_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.k_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.o_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.q_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.v_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| } |
| }, |
| { |
| "mlp.down_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.gate_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.up_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.k_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.o_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.q_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.v_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| } |
| }, |
| { |
| "mlp.down_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.gate_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.up_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.k_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.o_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.q_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.v_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| } |
| }, |
| { |
| "mlp.down_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.gate_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.up_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.k_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.o_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.q_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.v_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| } |
| }, |
| { |
| "mlp.down_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.gate_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.up_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.k_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.o_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.q_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.v_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| } |
| }, |
| { |
| "mlp.down_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.gate_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.up_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.k_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.o_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.q_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.v_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| } |
| }, |
| { |
| "mlp.down_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.gate_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.up_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.k_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.o_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.q_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.v_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| } |
| }, |
| { |
| "mlp.down_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.gate_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.up_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.k_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.o_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.q_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.v_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| } |
| }, |
| { |
| "mlp.down_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.gate_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.up_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.k_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.o_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.q_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.v_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| } |
| }, |
| { |
| "mlp.down_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.gate_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.up_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.k_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.o_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.q_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.v_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| } |
| }, |
| { |
| "mlp.down_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.gate_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.up_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.k_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.o_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.q_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.v_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| } |
| }, |
| { |
| "mlp.down_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.gate_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.up_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.k_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.o_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.q_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.v_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| } |
| }, |
| { |
| "mlp.down_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.gate_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.up_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.k_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.o_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.q_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.v_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| } |
| }, |
| { |
| "mlp.down_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.gate_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.up_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.k_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.o_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.q_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.v_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| } |
| }, |
| { |
| "mlp.down_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.gate_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.up_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.k_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.o_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.q_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.v_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| } |
| }, |
| { |
| "mlp.down_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.gate_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.up_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.k_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.o_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.q_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.v_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| } |
| }, |
| { |
| "mlp.down_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.gate_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.up_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.k_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.o_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.q_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.v_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| } |
| }, |
| { |
| "mlp.down_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.gate_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.up_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.k_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.o_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.q_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.v_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| } |
| }, |
| { |
| "mlp.down_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.gate_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.up_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.k_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.o_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.q_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.v_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| } |
| }, |
| { |
| "mlp.down_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.gate_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.up_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.k_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.o_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.q_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.v_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| } |
| }, |
| { |
| "mlp.down_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.gate_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.up_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.k_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.o_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.q_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.v_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| } |
| }, |
| { |
| "mlp.down_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.gate_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.up_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.k_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.o_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.q_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.v_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| } |
| }, |
| { |
| "mlp.down_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.gate_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.up_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.k_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.o_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.q_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.v_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| } |
| }, |
| { |
| "mlp.down_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.gate_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.up_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.k_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.o_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.q_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.v_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| } |
| }, |
| { |
| "mlp.down_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.gate_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.up_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.k_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.o_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.q_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.v_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| } |
| }, |
| { |
| "mlp.down_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.gate_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.up_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.k_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.o_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.q_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.v_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| } |
| }, |
| { |
| "mlp.down_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.gate_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.up_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.k_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.o_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.q_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.v_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| } |
| }, |
| { |
| "mlp.down_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.gate_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.up_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.k_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.o_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.q_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.v_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| } |
| }, |
| { |
| "mlp.down_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.gate_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "mlp.up_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.k_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.o_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.q_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| }, |
| "self_attn.v_proj": { |
| "bits": 4, |
| "method": "gptq", |
| "params": { |
| "group_size": 32 |
| } |
| } |
| } |
| ], |
| "quantized_layer_names": [ |
| "model.layers.0.mlp.down_proj", |
| "model.layers.0.mlp.gate_proj", |
| "model.layers.0.mlp.up_proj", |
| "model.layers.0.self_attn.k_proj", |
| "model.layers.0.self_attn.o_proj", |
| "model.layers.0.self_attn.q_proj", |
| "model.layers.0.self_attn.v_proj", |
| "model.layers.1.mlp.down_proj", |
| "model.layers.1.mlp.gate_proj", |
| "model.layers.1.mlp.up_proj", |
| "model.layers.1.self_attn.k_proj", |
| "model.layers.1.self_attn.o_proj", |
| "model.layers.1.self_attn.q_proj", |
| "model.layers.1.self_attn.v_proj", |
| "model.layers.10.mlp.down_proj", |
| "model.layers.10.mlp.gate_proj", |
| "model.layers.10.mlp.up_proj", |
| "model.layers.10.self_attn.k_proj", |
| "model.layers.10.self_attn.o_proj", |
| "model.layers.10.self_attn.q_proj", |
| "model.layers.10.self_attn.v_proj", |
| "model.layers.11.mlp.down_proj", |
| "model.layers.11.mlp.gate_proj", |
| "model.layers.11.mlp.up_proj", |
| "model.layers.11.self_attn.k_proj", |
| "model.layers.11.self_attn.o_proj", |
| "model.layers.11.self_attn.q_proj", |
| "model.layers.11.self_attn.v_proj", |
| "model.layers.12.mlp.down_proj", |
| "model.layers.12.mlp.gate_proj", |
| "model.layers.12.mlp.up_proj", |
| "model.layers.12.self_attn.k_proj", |
| "model.layers.12.self_attn.o_proj", |
| "model.layers.12.self_attn.q_proj", |
| "model.layers.12.self_attn.v_proj", |
| "model.layers.13.mlp.down_proj", |
| "model.layers.13.mlp.gate_proj", |
| "model.layers.13.mlp.up_proj", |
| "model.layers.13.self_attn.k_proj", |
| "model.layers.13.self_attn.o_proj", |
| "model.layers.13.self_attn.q_proj", |
| "model.layers.13.self_attn.v_proj", |
| "model.layers.14.mlp.down_proj", |
| "model.layers.14.mlp.gate_proj", |
| "model.layers.14.mlp.up_proj", |
| "model.layers.14.self_attn.k_proj", |
| "model.layers.14.self_attn.o_proj", |
| "model.layers.14.self_attn.q_proj", |
| "model.layers.14.self_attn.v_proj", |
| "model.layers.15.mlp.down_proj", |
| "model.layers.15.mlp.gate_proj", |
| "model.layers.15.mlp.up_proj", |
| "model.layers.15.self_attn.k_proj", |
| "model.layers.15.self_attn.o_proj", |
| "model.layers.15.self_attn.q_proj", |
| "model.layers.15.self_attn.v_proj", |
| "model.layers.16.mlp.down_proj", |
| "model.layers.16.mlp.gate_proj", |
| "model.layers.16.mlp.up_proj", |
| "model.layers.16.self_attn.k_proj", |
| "model.layers.16.self_attn.o_proj", |
| "model.layers.16.self_attn.q_proj", |
| "model.layers.16.self_attn.v_proj", |
| "model.layers.17.mlp.down_proj", |
| "model.layers.17.mlp.gate_proj", |
| "model.layers.17.mlp.up_proj", |
| "model.layers.17.self_attn.k_proj", |
| "model.layers.17.self_attn.o_proj", |
| "model.layers.17.self_attn.q_proj", |
| "model.layers.17.self_attn.v_proj", |
| "model.layers.18.mlp.down_proj", |
| "model.layers.18.mlp.gate_proj", |
| "model.layers.18.mlp.up_proj", |
| "model.layers.18.self_attn.k_proj", |
| "model.layers.18.self_attn.o_proj", |
| "model.layers.18.self_attn.q_proj", |
| "model.layers.18.self_attn.v_proj", |
| "model.layers.19.mlp.down_proj", |
| "model.layers.19.mlp.gate_proj", |
| "model.layers.19.mlp.up_proj", |
| "model.layers.19.self_attn.k_proj", |
| "model.layers.19.self_attn.o_proj", |
| "model.layers.19.self_attn.q_proj", |
| "model.layers.19.self_attn.v_proj", |
| "model.layers.2.mlp.down_proj", |
| "model.layers.2.mlp.gate_proj", |
| "model.layers.2.mlp.up_proj", |
| "model.layers.2.self_attn.k_proj", |
| "model.layers.2.self_attn.o_proj", |
| "model.layers.2.self_attn.q_proj", |
| "model.layers.2.self_attn.v_proj", |
| "model.layers.20.mlp.down_proj", |
| "model.layers.20.mlp.gate_proj", |
| "model.layers.20.mlp.up_proj", |
| "model.layers.20.self_attn.k_proj", |
| "model.layers.20.self_attn.o_proj", |
| "model.layers.20.self_attn.q_proj", |
| "model.layers.20.self_attn.v_proj", |
| "model.layers.21.mlp.down_proj", |
| "model.layers.21.mlp.gate_proj", |
| "model.layers.21.mlp.up_proj", |
| "model.layers.21.self_attn.k_proj", |
| "model.layers.21.self_attn.o_proj", |
| "model.layers.21.self_attn.q_proj", |
| "model.layers.21.self_attn.v_proj", |
| "model.layers.22.mlp.down_proj", |
| "model.layers.22.mlp.gate_proj", |
| "model.layers.22.mlp.up_proj", |
| "model.layers.22.self_attn.k_proj", |
| "model.layers.22.self_attn.o_proj", |
| "model.layers.22.self_attn.q_proj", |
| "model.layers.22.self_attn.v_proj", |
| "model.layers.23.mlp.down_proj", |
| "model.layers.23.mlp.gate_proj", |
| "model.layers.23.mlp.up_proj", |
| "model.layers.23.self_attn.k_proj", |
| "model.layers.23.self_attn.o_proj", |
| "model.layers.23.self_attn.q_proj", |
| "model.layers.23.self_attn.v_proj", |
| "model.layers.24.mlp.down_proj", |
| "model.layers.24.mlp.gate_proj", |
| "model.layers.24.mlp.up_proj", |
| "model.layers.24.self_attn.k_proj", |
| "model.layers.24.self_attn.o_proj", |
| "model.layers.24.self_attn.q_proj", |
| "model.layers.24.self_attn.v_proj", |
| "model.layers.25.mlp.down_proj", |
| "model.layers.25.mlp.gate_proj", |
| "model.layers.25.mlp.up_proj", |
| "model.layers.25.self_attn.k_proj", |
| "model.layers.25.self_attn.o_proj", |
| "model.layers.25.self_attn.q_proj", |
| "model.layers.25.self_attn.v_proj", |
| "model.layers.26.mlp.down_proj", |
| "model.layers.26.mlp.gate_proj", |
| "model.layers.26.mlp.up_proj", |
| "model.layers.26.self_attn.k_proj", |
| "model.layers.26.self_attn.o_proj", |
| "model.layers.26.self_attn.q_proj", |
| "model.layers.26.self_attn.v_proj", |
| "model.layers.27.mlp.down_proj", |
| "model.layers.27.mlp.gate_proj", |
| "model.layers.27.mlp.up_proj", |
| "model.layers.27.self_attn.k_proj", |
| "model.layers.27.self_attn.o_proj", |
| "model.layers.27.self_attn.q_proj", |
| "model.layers.27.self_attn.v_proj", |
| "model.layers.28.mlp.down_proj", |
| "model.layers.28.mlp.gate_proj", |
| "model.layers.28.mlp.up_proj", |
| "model.layers.28.self_attn.k_proj", |
| "model.layers.28.self_attn.o_proj", |
| "model.layers.28.self_attn.q_proj", |
| "model.layers.28.self_attn.v_proj", |
| "model.layers.29.mlp.down_proj", |
| "model.layers.29.mlp.gate_proj", |
| "model.layers.29.mlp.up_proj", |
| "model.layers.29.self_attn.k_proj", |
| "model.layers.29.self_attn.o_proj", |
| "model.layers.29.self_attn.q_proj", |
| "model.layers.29.self_attn.v_proj", |
| "model.layers.3.mlp.down_proj", |
| "model.layers.3.mlp.gate_proj", |
| "model.layers.3.mlp.up_proj", |
| "model.layers.3.self_attn.k_proj", |
| "model.layers.3.self_attn.o_proj", |
| "model.layers.3.self_attn.q_proj", |
| "model.layers.3.self_attn.v_proj", |
| "model.layers.30.mlp.down_proj", |
| "model.layers.30.mlp.gate_proj", |
| "model.layers.30.mlp.up_proj", |
| "model.layers.30.self_attn.k_proj", |
| "model.layers.30.self_attn.o_proj", |
| "model.layers.30.self_attn.q_proj", |
| "model.layers.30.self_attn.v_proj", |
| "model.layers.31.mlp.down_proj", |
| "model.layers.31.mlp.gate_proj", |
| "model.layers.31.mlp.up_proj", |
| "model.layers.31.self_attn.k_proj", |
| "model.layers.31.self_attn.o_proj", |
| "model.layers.31.self_attn.q_proj", |
| "model.layers.31.self_attn.v_proj", |
| "model.layers.32.mlp.down_proj", |
| "model.layers.32.mlp.gate_proj", |
| "model.layers.32.mlp.up_proj", |
| "model.layers.32.self_attn.k_proj", |
| "model.layers.32.self_attn.o_proj", |
| "model.layers.32.self_attn.q_proj", |
| "model.layers.32.self_attn.v_proj", |
| "model.layers.33.mlp.down_proj", |
| "model.layers.33.mlp.gate_proj", |
| "model.layers.33.mlp.up_proj", |
| "model.layers.33.self_attn.k_proj", |
| "model.layers.33.self_attn.o_proj", |
| "model.layers.33.self_attn.q_proj", |
| "model.layers.33.self_attn.v_proj", |
| "model.layers.34.mlp.down_proj", |
| "model.layers.34.mlp.gate_proj", |
| "model.layers.34.mlp.up_proj", |
| "model.layers.34.self_attn.k_proj", |
| "model.layers.34.self_attn.o_proj", |
| "model.layers.34.self_attn.q_proj", |
| "model.layers.34.self_attn.v_proj", |
| "model.layers.35.mlp.down_proj", |
| "model.layers.35.mlp.gate_proj", |
| "model.layers.35.mlp.up_proj", |
| "model.layers.35.self_attn.k_proj", |
| "model.layers.35.self_attn.o_proj", |
| "model.layers.35.self_attn.q_proj", |
| "model.layers.35.self_attn.v_proj", |
| "model.layers.4.mlp.down_proj", |
| "model.layers.4.mlp.gate_proj", |
| "model.layers.4.mlp.up_proj", |
| "model.layers.4.self_attn.k_proj", |
| "model.layers.4.self_attn.o_proj", |
| "model.layers.4.self_attn.q_proj", |
| "model.layers.4.self_attn.v_proj", |
| "model.layers.5.mlp.down_proj", |
| "model.layers.5.mlp.gate_proj", |
| "model.layers.5.mlp.up_proj", |
| "model.layers.5.self_attn.k_proj", |
| "model.layers.5.self_attn.o_proj", |
| "model.layers.5.self_attn.q_proj", |
| "model.layers.5.self_attn.v_proj", |
| "model.layers.6.mlp.down_proj", |
| "model.layers.6.mlp.gate_proj", |
| "model.layers.6.mlp.up_proj", |
| "model.layers.6.self_attn.k_proj", |
| "model.layers.6.self_attn.o_proj", |
| "model.layers.6.self_attn.q_proj", |
| "model.layers.6.self_attn.v_proj", |
| "model.layers.7.mlp.down_proj", |
| "model.layers.7.mlp.gate_proj", |
| "model.layers.7.mlp.up_proj", |
| "model.layers.7.self_attn.k_proj", |
| "model.layers.7.self_attn.o_proj", |
| "model.layers.7.self_attn.q_proj", |
| "model.layers.7.self_attn.v_proj", |
| "model.layers.8.mlp.down_proj", |
| "model.layers.8.mlp.gate_proj", |
| "model.layers.8.mlp.up_proj", |
| "model.layers.8.self_attn.k_proj", |
| "model.layers.8.self_attn.o_proj", |
| "model.layers.8.self_attn.q_proj", |
| "model.layers.8.self_attn.v_proj", |
| "model.layers.9.mlp.down_proj", |
| "model.layers.9.mlp.gate_proj", |
| "model.layers.9.mlp.up_proj", |
| "model.layers.9.self_attn.k_proj", |
| "model.layers.9.self_attn.o_proj", |
| "model.layers.9.self_attn.q_proj", |
| "model.layers.9.self_attn.v_proj" |
| ], |
| "rotated": false, |
| "sym": true |
| }, |
| "rms_norm_eps": 1e-06, |
| "rope_parameters": { |
| "rope_theta": 1000000, |
| "rope_type": "default" |
| }, |
| "sliding_window": null, |
| "tie_word_embeddings": true, |
| "transformers_version": "5.8.1", |
| "use_cache": true, |
| "use_sliding_window": false, |
| "vocab_size": 151936 |
| } |
|
|
