{ "config_groups": { "group_0": { "targets": [ "Linear" ], "weights": { "num_bits": 8, "type": "float", "symmetric": true, "group_size": 32, "strategy": "group", "block_structure": null, "dynamic": false, "actorder": null, "scale_dtype": "torch.uint8", "zp_dtype": null, "observer": "memoryless_minmax", "observer_kwargs": {} }, "input_activations": { "num_bits": 8, "type": "float", "symmetric": true, "group_size": 32, "strategy": "group", "block_structure": null, "dynamic": true, "actorder": null, "scale_dtype": "torch.uint8", "zp_dtype": null, "observer": null, "observer_kwargs": {} }, "output_activations": null, "format": null } }, "quant_method": "compressed-tensors", "kv_cache_scheme": null, "format": "mxfp8-quantized", "quantization_status": "compressed", "global_compression_ratio": null, "ignore": [ "lm_head", "model.embed_tokens", "model.layers.1.mlp.gate", "model.layers.10.mlp.gate", "model.layers.11.mlp.gate", "model.layers.2.mlp.gate", "model.layers.3.mlp.gate", "model.layers.4.mlp.gate", "model.layers.5.mlp.gate", "model.layers.6.mlp.gate", "model.layers.7.mlp.gate", "model.layers.8.mlp.gate", "model.layers.9.mlp.gate", "model.projector.layers", "model.qwen2_model.model.model.layers.0.mlp.down_proj", "model.qwen2_model.model.model.layers.0.mlp.gate_proj", "model.qwen2_model.model.model.layers.0.mlp.up_proj", "model.qwen2_model.model.model.layers.0.self_attn.k_proj", "model.qwen2_model.model.model.layers.0.self_attn.o_proj", "model.qwen2_model.model.model.layers.0.self_attn.q_proj", "model.qwen2_model.model.model.layers.0.self_attn.v_proj", "model.qwen2_model.model.model.layers.1.mlp.down_proj", "model.qwen2_model.model.model.layers.1.mlp.gate_proj", "model.qwen2_model.model.model.layers.1.mlp.up_proj", "model.qwen2_model.model.model.layers.1.self_attn.k_proj", "model.qwen2_model.model.model.layers.1.self_attn.o_proj", "model.qwen2_model.model.model.layers.1.self_attn.q_proj", "model.qwen2_model.model.model.layers.1.self_attn.v_proj", "model.qwen2_model.model.model.layers.10.mlp.down_proj", "model.qwen2_model.model.model.layers.10.mlp.gate_proj", "model.qwen2_model.model.model.layers.10.mlp.up_proj", "model.qwen2_model.model.model.layers.10.self_attn.k_proj", "model.qwen2_model.model.model.layers.10.self_attn.o_proj", "model.qwen2_model.model.model.layers.10.self_attn.q_proj", "model.qwen2_model.model.model.layers.10.self_attn.v_proj", "model.qwen2_model.model.model.layers.11.mlp.down_proj", "model.qwen2_model.model.model.layers.11.mlp.gate_proj", "model.qwen2_model.model.model.layers.11.mlp.up_proj", "model.qwen2_model.model.model.layers.11.self_attn.k_proj", "model.qwen2_model.model.model.layers.11.self_attn.o_proj", "model.qwen2_model.model.model.layers.11.self_attn.q_proj", "model.qwen2_model.model.model.layers.11.self_attn.v_proj", "model.qwen2_model.model.model.layers.12.mlp.down_proj", "model.qwen2_model.model.model.layers.12.mlp.gate_proj", "model.qwen2_model.model.model.layers.12.mlp.up_proj", "model.qwen2_model.model.model.layers.12.self_attn.k_proj", "model.qwen2_model.model.model.layers.12.self_attn.o_proj", "model.qwen2_model.model.model.layers.12.self_attn.q_proj", "model.qwen2_model.model.model.layers.12.self_attn.v_proj", "model.qwen2_model.model.model.layers.13.mlp.down_proj", "model.qwen2_model.model.model.layers.13.mlp.gate_proj", "model.qwen2_model.model.model.layers.13.mlp.up_proj", "model.qwen2_model.model.model.layers.13.self_attn.k_proj", "model.qwen2_model.model.model.layers.13.self_attn.o_proj", "model.qwen2_model.model.model.layers.13.self_attn.q_proj", "model.qwen2_model.model.model.layers.13.self_attn.v_proj", "model.qwen2_model.model.model.layers.14.mlp.down_proj", "model.qwen2_model.model.model.layers.14.mlp.gate_proj", "model.qwen2_model.model.model.layers.14.mlp.up_proj", "model.qwen2_model.model.model.layers.14.self_attn.k_proj", "model.qwen2_model.model.model.layers.14.self_attn.o_proj", "model.qwen2_model.model.model.layers.14.self_attn.q_proj", "model.qwen2_model.model.model.layers.14.self_attn.v_proj", "model.qwen2_model.model.model.layers.15.mlp.down_proj", "model.qwen2_model.model.model.layers.15.mlp.gate_proj", "model.qwen2_model.model.model.layers.15.mlp.up_proj", "model.qwen2_model.model.model.layers.15.self_attn.k_proj", "model.qwen2_model.model.model.layers.15.self_attn.o_proj", "model.qwen2_model.model.model.layers.15.self_attn.q_proj", "model.qwen2_model.model.model.layers.15.self_attn.v_proj", "model.qwen2_model.model.model.layers.16.mlp.down_proj", "model.qwen2_model.model.model.layers.16.mlp.gate_proj", "model.qwen2_model.model.model.layers.16.mlp.up_proj", "model.qwen2_model.model.model.layers.16.self_attn.k_proj", "model.qwen2_model.model.model.layers.16.self_attn.o_proj", "model.qwen2_model.model.model.layers.16.self_attn.q_proj", "model.qwen2_model.model.model.layers.16.self_attn.v_proj", "model.qwen2_model.model.model.layers.17.mlp.down_proj", "model.qwen2_model.model.model.layers.17.mlp.gate_proj", "model.qwen2_model.model.model.layers.17.mlp.up_proj", "model.qwen2_model.model.model.layers.17.self_attn.k_proj", "model.qwen2_model.model.model.layers.17.self_attn.o_proj", "model.qwen2_model.model.model.layers.17.self_attn.q_proj", "model.qwen2_model.model.model.layers.17.self_attn.v_proj", "model.qwen2_model.model.model.layers.18.mlp.down_proj", "model.qwen2_model.model.model.layers.18.mlp.gate_proj", "model.qwen2_model.model.model.layers.18.mlp.up_proj", "model.qwen2_model.model.model.layers.18.self_attn.k_proj", "model.qwen2_model.model.model.layers.18.self_attn.o_proj", "model.qwen2_model.model.model.layers.18.self_attn.q_proj", "model.qwen2_model.model.model.layers.18.self_attn.v_proj", "model.qwen2_model.model.model.layers.19.mlp.down_proj", "model.qwen2_model.model.model.layers.19.mlp.gate_proj", "model.qwen2_model.model.model.layers.19.mlp.up_proj", "model.qwen2_model.model.model.layers.19.self_attn.k_proj", "model.qwen2_model.model.model.layers.19.self_attn.o_proj", "model.qwen2_model.model.model.layers.19.self_attn.q_proj", "model.qwen2_model.model.model.layers.19.self_attn.v_proj", "model.qwen2_model.model.model.layers.2.mlp.down_proj", "model.qwen2_model.model.model.layers.2.mlp.gate_proj", "model.qwen2_model.model.model.layers.2.mlp.up_proj", "model.qwen2_model.model.model.layers.2.self_attn.k_proj", "model.qwen2_model.model.model.layers.2.self_attn.o_proj", "model.qwen2_model.model.model.layers.2.self_attn.q_proj", "model.qwen2_model.model.model.layers.2.self_attn.v_proj", "model.qwen2_model.model.model.layers.20.mlp.down_proj", "model.qwen2_model.model.model.layers.20.mlp.gate_proj", "model.qwen2_model.model.model.layers.20.mlp.up_proj", "model.qwen2_model.model.model.layers.20.self_attn.k_proj", "model.qwen2_model.model.model.layers.20.self_attn.o_proj", "model.qwen2_model.model.model.layers.20.self_attn.q_proj", "model.qwen2_model.model.model.layers.20.self_attn.v_proj", "model.qwen2_model.model.model.layers.21.mlp.down_proj", "model.qwen2_model.model.model.layers.21.mlp.gate_proj", "model.qwen2_model.model.model.layers.21.mlp.up_proj", "model.qwen2_model.model.model.layers.21.self_attn.k_proj", "model.qwen2_model.model.model.layers.21.self_attn.o_proj", "model.qwen2_model.model.model.layers.21.self_attn.q_proj", "model.qwen2_model.model.model.layers.21.self_attn.v_proj", "model.qwen2_model.model.model.layers.22.mlp.down_proj", "model.qwen2_model.model.model.layers.22.mlp.gate_proj", "model.qwen2_model.model.model.layers.22.mlp.up_proj", "model.qwen2_model.model.model.layers.22.self_attn.k_proj", "model.qwen2_model.model.model.layers.22.self_attn.o_proj", "model.qwen2_model.model.model.layers.22.self_attn.q_proj", "model.qwen2_model.model.model.layers.22.self_attn.v_proj", "model.qwen2_model.model.model.layers.23.mlp.down_proj", "model.qwen2_model.model.model.layers.23.mlp.gate_proj", "model.qwen2_model.model.model.layers.23.mlp.up_proj", "model.qwen2_model.model.model.layers.23.self_attn.k_proj", "model.qwen2_model.model.model.layers.23.self_attn.o_proj", "model.qwen2_model.model.model.layers.23.self_attn.q_proj", "model.qwen2_model.model.model.layers.23.self_attn.v_proj", "model.qwen2_model.model.model.layers.3.mlp.down_proj", "model.qwen2_model.model.model.layers.3.mlp.gate_proj", "model.qwen2_model.model.model.layers.3.mlp.up_proj", "model.qwen2_model.model.model.layers.3.self_attn.k_proj", "model.qwen2_model.model.model.layers.3.self_attn.o_proj", "model.qwen2_model.model.model.layers.3.self_attn.q_proj", "model.qwen2_model.model.model.layers.3.self_attn.v_proj", "model.qwen2_model.model.model.layers.4.mlp.down_proj", "model.qwen2_model.model.model.layers.4.mlp.gate_proj", "model.qwen2_model.model.model.layers.4.mlp.up_proj", "model.qwen2_model.model.model.layers.4.self_attn.k_proj", "model.qwen2_model.model.model.layers.4.self_attn.o_proj", "model.qwen2_model.model.model.layers.4.self_attn.q_proj", "model.qwen2_model.model.model.layers.4.self_attn.v_proj", "model.qwen2_model.model.model.layers.5.mlp.down_proj", "model.qwen2_model.model.model.layers.5.mlp.gate_proj", "model.qwen2_model.model.model.layers.5.mlp.up_proj", "model.qwen2_model.model.model.layers.5.self_attn.k_proj", "model.qwen2_model.model.model.layers.5.self_attn.o_proj", "model.qwen2_model.model.model.layers.5.self_attn.q_proj", "model.qwen2_model.model.model.layers.5.self_attn.v_proj", "model.qwen2_model.model.model.layers.6.mlp.down_proj", "model.qwen2_model.model.model.layers.6.mlp.gate_proj", "model.qwen2_model.model.model.layers.6.mlp.up_proj", "model.qwen2_model.model.model.layers.6.self_attn.k_proj", "model.qwen2_model.model.model.layers.6.self_attn.o_proj", "model.qwen2_model.model.model.layers.6.self_attn.q_proj", "model.qwen2_model.model.model.layers.6.self_attn.v_proj", "model.qwen2_model.model.model.layers.7.mlp.down_proj", "model.qwen2_model.model.model.layers.7.mlp.gate_proj", "model.qwen2_model.model.model.layers.7.mlp.up_proj", "model.qwen2_model.model.model.layers.7.self_attn.k_proj", "model.qwen2_model.model.model.layers.7.self_attn.o_proj", "model.qwen2_model.model.model.layers.7.self_attn.q_proj", "model.qwen2_model.model.model.layers.7.self_attn.v_proj", "model.qwen2_model.model.model.layers.8.mlp.down_proj", "model.qwen2_model.model.model.layers.8.mlp.gate_proj", "model.qwen2_model.model.model.layers.8.mlp.up_proj", "model.qwen2_model.model.model.layers.8.self_attn.k_proj", "model.qwen2_model.model.model.layers.8.self_attn.o_proj", "model.qwen2_model.model.model.layers.8.self_attn.q_proj", "model.qwen2_model.model.model.layers.8.self_attn.v_proj", "model.qwen2_model.model.model.layers.9.mlp.down_proj", "model.qwen2_model.model.model.layers.9.mlp.gate_proj", "model.qwen2_model.model.model.layers.9.mlp.up_proj", "model.qwen2_model.model.model.layers.9.self_attn.k_proj", "model.qwen2_model.model.model.layers.9.self_attn.o_proj", "model.qwen2_model.model.model.layers.9.self_attn.q_proj", "model.qwen2_model.model.model.layers.9.self_attn.v_proj", "model.qwen2_model.query_1024", "model.qwen2_model.query_768", "model.sam_model.blocks.0.attn.proj", "model.sam_model.blocks.0.attn.qkv", "model.sam_model.blocks.0.mlp.lin1", "model.sam_model.blocks.0.mlp.lin2", "model.sam_model.blocks.1.attn.proj", "model.sam_model.blocks.1.attn.qkv", "model.sam_model.blocks.1.mlp.lin1", "model.sam_model.blocks.1.mlp.lin2", "model.sam_model.blocks.10.attn.proj", "model.sam_model.blocks.10.attn.qkv", "model.sam_model.blocks.10.mlp.lin1", "model.sam_model.blocks.10.mlp.lin2", "model.sam_model.blocks.11.attn.proj", "model.sam_model.blocks.11.attn.qkv", "model.sam_model.blocks.11.mlp.lin1", "model.sam_model.blocks.11.mlp.lin2", "model.sam_model.blocks.2.attn.proj", "model.sam_model.blocks.2.attn.qkv", "model.sam_model.blocks.2.mlp.lin1", "model.sam_model.blocks.2.mlp.lin2", "model.sam_model.blocks.3.attn.proj", "model.sam_model.blocks.3.attn.qkv", "model.sam_model.blocks.3.mlp.lin1", "model.sam_model.blocks.3.mlp.lin2", "model.sam_model.blocks.4.attn.proj", "model.sam_model.blocks.4.attn.qkv", "model.sam_model.blocks.4.mlp.lin1", "model.sam_model.blocks.4.mlp.lin2", "model.sam_model.blocks.5.attn.proj", "model.sam_model.blocks.5.attn.qkv", "model.sam_model.blocks.5.mlp.lin1", "model.sam_model.blocks.5.mlp.lin2", "model.sam_model.blocks.6.attn.proj", "model.sam_model.blocks.6.attn.qkv", "model.sam_model.blocks.6.mlp.lin1", "model.sam_model.blocks.6.mlp.lin2", "model.sam_model.blocks.7.attn.proj", "model.sam_model.blocks.7.attn.qkv", "model.sam_model.blocks.7.mlp.lin1", "model.sam_model.blocks.7.mlp.lin2", "model.sam_model.blocks.8.attn.proj", "model.sam_model.blocks.8.attn.qkv", "model.sam_model.blocks.8.mlp.lin1", "model.sam_model.blocks.8.mlp.lin2", "model.sam_model.blocks.9.attn.proj", "model.sam_model.blocks.9.attn.qkv", "model.sam_model.blocks.9.mlp.lin1", "model.sam_model.blocks.9.mlp.lin2", "model.sam_model.neck.0", "model.sam_model.neck.2", "model.sam_model.net_2", "model.sam_model.net_3", "model.sam_model.patch_embed.proj" ], "provider": "auto-round" }