Hy4-flash-NVFP4 / quant_config.json
Avifenesh's picture
Model card and quantization config
7c809f2 verified
Raw History Blame Contribute Delete
42.1 kB
{ "producer": { "repo": "Avifenesh/Hy4-flash-NVFP4", "date": "2026-11-18", "source": "tencent/Hy4-flash@d88c9dfd96ba4f2e6b92adba0b8e8f1c8696f959", "note": "Modified from tencent/Hy4-flash: weights quantized as listed below; see README.md" }, "quantization": { "quant_algo": "MIXED_PRECISION", "kv_cache_quant_algo": null, "activations": "not quantized (weight-only)", "layout": "LAYOUT.md", "quantized_layers": { "model.dfly_layers.0.mlp.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per tensor" }, "model.dfly_layers.0.mlp.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per tensor" }, "model.dfly_layers.0.mlp.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per tensor" }, "model.dfly_layers.0.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.dfly_layers.0.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.dfly_layers.0.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.dfly_layers.1.mlp.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per tensor" }, "model.dfly_layers.1.mlp.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per tensor" }, "model.dfly_layers.1.mlp.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per tensor" }, "model.dfly_layers.1.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.dfly_layers.1.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.dfly_layers.1.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.dfly_layers.2.mlp.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per tensor" }, "model.dfly_layers.2.mlp.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per tensor" }, "model.dfly_layers.2.mlp.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per tensor" }, "model.dfly_layers.2.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.dfly_layers.2.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.dfly_layers.2.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.dfly_layers.3.mlp.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per tensor" }, "model.dfly_layers.3.mlp.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per tensor" }, "model.dfly_layers.3.mlp.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per tensor" }, "model.dfly_layers.3.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.dfly_layers.3.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.dfly_layers.3.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.dfly_layers.4.mlp.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per tensor" }, "model.dfly_layers.4.mlp.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per tensor" }, "model.dfly_layers.4.mlp.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per tensor" }, "model.dfly_layers.4.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.dfly_layers.4.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.dfly_layers.4.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.dfly_layers.hidden_correction.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per tensor" }, "model.dfly_layers.hidden_correction.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per tensor" }, "model.dfly_layers.hidden_correction.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per tensor" }, "model.layers.1.engram_layer.multi_head_embedding.embedding": { "quant_algo": "FP8_ROW" }, "model.layers.1.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.1.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.1.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.1.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.1.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.1.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.10.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.10.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.10.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.10.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.10.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.10.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.11.engram_layer.multi_head_embedding.embedding": { "quant_algo": "FP8_ROW" }, "model.layers.11.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.11.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.11.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.11.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.11.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.11.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.12.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.12.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.12.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.12.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.12.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.12.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.13.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.13.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.13.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.13.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.13.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.13.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.14.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.14.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.14.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.14.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.14.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.14.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.15.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.15.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.15.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.15.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.15.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.15.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.16.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.16.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.16.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.16.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.16.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.16.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.17.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.17.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.17.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.17.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.17.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.17.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.18.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.18.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.18.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.18.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.18.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.18.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.19.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.19.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.19.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.19.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.19.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.19.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.2.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.2.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.2.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.2.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.2.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.2.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.20.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.20.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.20.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.20.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.20.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.20.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.21.engram_layer.multi_head_embedding.embedding": { "quant_algo": "FP8_ROW" }, "model.layers.21.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.21.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.21.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.21.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.21.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.21.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.22.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.22.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.22.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.22.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.22.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.22.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.23.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.23.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.23.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.23.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.23.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.23.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.24.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.24.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.24.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.24.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.24.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.24.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.25.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.25.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.25.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.25.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.25.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.25.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.26.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.26.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.26.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.26.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.26.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.26.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.27.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.27.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.27.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.27.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.27.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.27.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.28.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.28.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.28.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.28.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.28.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.28.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.29.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.29.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.29.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.29.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.29.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.29.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.3.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.3.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.3.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.3.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.3.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.3.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.30.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.30.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.30.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.30.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.30.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.30.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.31.engram_layer.multi_head_embedding.embedding": { "quant_algo": "FP8_ROW" }, "model.layers.31.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.31.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.31.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.31.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.31.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.31.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.32.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.32.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.32.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.32.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.32.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.32.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.33.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.33.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.33.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.33.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.33.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.33.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.34.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.34.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.34.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.34.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.34.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.34.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.35.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.35.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.35.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.35.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.35.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.35.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.36.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.36.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.36.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.36.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.36.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.36.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.37.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.37.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.37.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.37.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.37.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.37.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.38.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.38.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.38.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.38.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.38.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.38.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.39.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.39.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.39.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.39.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.39.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.39.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.4.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.4.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.4.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.4.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.4.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.4.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.40.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.40.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.40.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.40.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.40.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.40.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.41.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.41.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.41.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.41.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.41.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.41.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.5.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.5.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.5.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.5.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.5.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.5.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.6.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.6.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.6.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.6.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.6.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.6.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.7.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.7.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.7.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.7.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.7.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.7.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.8.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.8.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.8.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.8.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.8.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.8.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.9.mlp.experts.down_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.9.mlp.experts.gate_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.9.mlp.experts.up_proj": { "quant_algo": "NVFP4", "group_size": 16, "weight_scale": "E4M3 per 16", "weight_scale_2": "FP32 per expert" }, "model.layers.9.self_attn.linear_gate": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.9.self_attn.o_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] }, "model.layers.9.self_attn.q_b_proj": { "quant_algo": "FP8_BLOCK", "block": [ 128, 128 ] } } } }
{
"producer": {
"repo": "Avifenesh/Hy4-flash-NVFP4",
"date": "2026-11-18",
"source": "tencent/Hy4-flash@d88c9dfd96ba4f2e6b92adba0b8e8f1c8696f959",
"note": "Modified from tencent/Hy4-flash: weights quantized as listed below; see README.md"
},
"quantization": {
"quant_algo": "MIXED_PRECISION",
"kv_cache_quant_algo": null,
"activations": "not quantized (weight-only)",
"layout": "LAYOUT.md",
"quantized_layers": {
"model.dfly_layers.0.mlp.down_proj": {
"quant_algo": "NVFP4",
"group_size": 16,
"weight_scale": "E4M3 per 16",
"weight_scale_2": "FP32 per tensor"
},
"model.dfly_layers.0.mlp.gate_proj": {
"quant_algo": "NVFP4",
"group_size": 16,
"weight_scale": "E4M3 per 16",
"weight_scale_2": "FP32 per tensor"
},
"model.dfly_layers.0.mlp.up_proj": {
"quant_algo": "NVFP4",
"group_size": 16,
"weight_scale": "E4M3 per 16",
"weight_scale_2": "FP32 per tensor"
},
"model.dfly_layers.0.self_attn.linear_gate": {
"quant_algo": "FP8_BLOCK",
"block": [
128,
128
]
},
"model.dfly_layers.0.self_attn.o_proj": {
"quant_algo": "FP8_BLOCK",
"block": [
128,
128
]
},
"model.dfly_layers.0.self_attn.q_b_proj": {
"quant_algo": "FP8_BLOCK",
"block": [
128,
128
]
},
"model.dfly_layers.1.mlp.down_proj": {
"quant_algo": "NVFP4",
"group_size": 16,
"weight_scale": "E4M3 per 16",
"weight_scale_2": "FP32 per tensor"
},
"model.dfly_layers.1.mlp.gate_proj": {
"quant_algo": "NVFP4",
"group_size": 16,
"weight_scale": "E4M3 per 16",
"weight_scale_2": "FP32 per tensor"
},
"model.dfly_layers.1.mlp.up_proj": {
"quant_algo": "NVFP4",
"group_size": 16,
"weight_scale": "E4M3 per 16",
"weight_scale_2": "FP32 per tensor"
},
"model.dfly_layers.1.self_attn.linear_gate": {
"quant_algo": "FP8_BLOCK",
"block": [
128,
128
]
},
"model.dfly_layers.1.self_attn.o_proj": {
"quant_algo": "FP8_BLOCK",
"block": [
128,
128
]
},
"model.dfly_layers.1.self_attn.q_b_proj": {
"quant_algo": "FP8_BLOCK",
"block": [
128,
128
]
},
"model.dfly_layers.2.mlp.down_proj": {
"quant_algo": "NVFP4",
"group_size": 16,
"weight_scale": "E4M3 per 16",
"weight_scale_2": "FP32 per tensor"
},
"model.dfly_layers.2.mlp.gate_proj": {
"quant_algo": "NVFP4",
"group_size": 16,