DeepSeek-V4-Flash-0731-AutoRound-W4A16 / quantization_config.json
bullerwins's picture
Add files using upload-large-folder tool
331f482 verified
Raw
History Blame
21.7 kB
{
"quant_method": "auto-round",
"packing_format": "auto_round:auto_gptq",
"bits": 4,
"group_size": 128,
"sym": true,
"data_type": "int",
"iters": 0,
"model_free": true,
"autoround_version": "0.15.0",
"extra_config": {
"wo_a": {
"bits": 16
},
"layers.0.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.0.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.6.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.6.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.6.attn.indexer.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.6.attn.indexer.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.6.attn.indexer.weights_proj": {
"bits": 16,
"data_type": "float"
},
"layers.6.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.6.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.5.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.5.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.5.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.5.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.1.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.1.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.7.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.7.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.7.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.7.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.4.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.4.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.4.attn.indexer.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.4.attn.indexer.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.4.attn.indexer.weights_proj": {
"bits": 16,
"data_type": "float"
},
"layers.4.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.4.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.3.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.3.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.3.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.3.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.2.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.2.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.2.attn.indexer.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.2.attn.indexer.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.2.attn.indexer.weights_proj": {
"bits": 16,
"data_type": "float"
},
"layers.2.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.2.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.8.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.8.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.8.attn.indexer.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.8.attn.indexer.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.8.attn.indexer.weights_proj": {
"bits": 16,
"data_type": "float"
},
"layers.8.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.8.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.9.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.9.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.9.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.9.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.10.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.10.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.10.attn.indexer.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.10.attn.indexer.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.10.attn.indexer.weights_proj": {
"bits": 16,
"data_type": "float"
},
"layers.10.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.10.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.11.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.11.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.11.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.11.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.12.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.12.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.12.attn.indexer.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.12.attn.indexer.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.12.attn.indexer.weights_proj": {
"bits": 16,
"data_type": "float"
},
"layers.12.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.12.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.13.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.13.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.13.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.13.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.15.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.15.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.15.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.15.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.16.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.16.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.16.attn.indexer.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.16.attn.indexer.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.16.attn.indexer.weights_proj": {
"bits": 16,
"data_type": "float"
},
"layers.16.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.16.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.14.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.14.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.14.attn.indexer.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.14.attn.indexer.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.14.attn.indexer.weights_proj": {
"bits": 16,
"data_type": "float"
},
"layers.14.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.14.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.17.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.17.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.17.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.17.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.18.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.18.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.18.attn.indexer.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.18.attn.indexer.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.18.attn.indexer.weights_proj": {
"bits": 16,
"data_type": "float"
},
"layers.18.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.18.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.19.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.19.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.19.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.19.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.24.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.24.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.24.attn.indexer.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.24.attn.indexer.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.24.attn.indexer.weights_proj": {
"bits": 16,
"data_type": "float"
},
"layers.24.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.24.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.20.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.20.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.20.attn.indexer.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.20.attn.indexer.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.20.attn.indexer.weights_proj": {
"bits": 16,
"data_type": "float"
},
"layers.20.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.20.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.21.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.21.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.21.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.21.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.22.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.22.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.22.attn.indexer.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.22.attn.indexer.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.22.attn.indexer.weights_proj": {
"bits": 16,
"data_type": "float"
},
"layers.22.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.22.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.23.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.23.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.23.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.23.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.25.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.25.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.25.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.25.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.26.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.26.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.26.attn.indexer.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.26.attn.indexer.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.26.attn.indexer.weights_proj": {
"bits": 16,
"data_type": "float"
},
"layers.26.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.26.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.27.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.27.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.27.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.27.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.28.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.28.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.28.attn.indexer.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.28.attn.indexer.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.28.attn.indexer.weights_proj": {
"bits": 16,
"data_type": "float"
},
"layers.28.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.28.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.29.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.29.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.29.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.29.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.31.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.31.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.31.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.31.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.30.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.30.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.30.attn.indexer.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.30.attn.indexer.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.30.attn.indexer.weights_proj": {
"bits": 16,
"data_type": "float"
},
"layers.30.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.30.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.32.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.32.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.32.attn.indexer.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.32.attn.indexer.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.32.attn.indexer.weights_proj": {
"bits": 16,
"data_type": "float"
},
"layers.32.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.32.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.33.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.33.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.33.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.33.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.35.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.35.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.35.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.35.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.34.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.34.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.34.attn.indexer.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.34.attn.indexer.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.34.attn.indexer.weights_proj": {
"bits": 16,
"data_type": "float"
},
"layers.34.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.34.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.37.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.37.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.37.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.37.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.36.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.36.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.36.attn.indexer.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.36.attn.indexer.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.36.attn.indexer.weights_proj": {
"bits": 16,
"data_type": "float"
},
"layers.36.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.36.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"head": {
"bits": 16,
"data_type": "float"
},
"layers.38.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.38.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.38.attn.indexer.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.38.attn.indexer.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.38.attn.indexer.weights_proj": {
"bits": 16,
"data_type": "float"
},
"layers.38.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.38.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.39.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.39.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.39.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.39.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.40.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.40.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.40.attn.indexer.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.40.attn.indexer.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.40.attn.indexer.weights_proj": {
"bits": 16,
"data_type": "float"
},
"layers.40.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.40.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.41.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.41.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.41.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.41.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"layers.42.attn.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.42.attn.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.42.attn.indexer.compressor.wgate": {
"bits": 16,
"data_type": "float"
},
"layers.42.attn.indexer.compressor.wkv": {
"bits": 16,
"data_type": "float"
},
"layers.42.attn.indexer.weights_proj": {
"bits": 16,
"data_type": "float"
},
"layers.42.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"layers.42.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"mtp.0.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"mtp.0.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"mtp.1.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"mtp.1.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"mtp.2.attn.wo_a": {
"bits": 16,
"data_type": "float"
},
"mtp.2.confidence_head.proj": {
"bits": 16,
"data_type": "float"
},
"mtp.2.ffn.gate": {
"bits": 16,
"data_type": "float"
},
"mtp.2.markov_head.markov_w1": {
"bits": 16,
"data_type": "float"
},
"mtp.2.markov_head.markov_w2": {
"bits": 16,
"data_type": "float"
}
}
}