TheDrummer_Valkyrie-49B-v1_EXL3_4.0bpw_H8 / quantization_config.json
ArtusDev's picture
Upload folder using huggingface_hub
a626d65 verified
Raw
History Blame Contribute Delete
464 kB
{
"quant_method": "exl3",
"version": "0.0.2",
"bits": 4.0,
"head_bits": 8,
"calibration": {
"rows": 100,
"cols": 2048
},
"out_scales": "auto",
"tensor_storage": {
"model.embed_tokens": {
"stored_tensors": {
"model.embed_tokens.weight": {
"shape": [
128256,
8192
],
"n_bytes": 2101346304,
"dtype": "torch.float16"
}
}
},
"model.layers.0.input_layernorm": {
"stored_tensors": {
"model.layers.0.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.0.self_attn.q_proj": {
"stored_tensors": {
"model.layers.0.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.0.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.0.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.0.self_attn.k_proj": {
"stored_tensors": {
"model.layers.0.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.0.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.0.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.0.self_attn.v_proj": {
"stored_tensors": {
"model.layers.0.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.0.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.0.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.0.self_attn.o_proj": {
"stored_tensors": {
"model.layers.0.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.0.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.0.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.0.post_attention_layernorm": {
"stored_tensors": {
"model.layers.0.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.0.mlp.up_proj": {
"stored_tensors": {
"model.layers.0.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.0.mlp.up_proj.svh": {
"shape": [
14336
],
"n_bytes": 28672,
"dtype": "torch.float16"
},
"model.layers.0.mlp.up_proj.trellis": {
"shape": [
512,
896,
64
],
"n_bytes": 58720256,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.0.mlp.gate_proj": {
"stored_tensors": {
"model.layers.0.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.0.mlp.gate_proj.svh": {
"shape": [
14336
],
"n_bytes": 28672,
"dtype": "torch.float16"
},
"model.layers.0.mlp.gate_proj.trellis": {
"shape": [
512,
896,
64
],
"n_bytes": 58720256,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.0.mlp.down_proj": {
"stored_tensors": {
"model.layers.0.mlp.down_proj.suh": {
"shape": [
14336
],
"n_bytes": 28672,
"dtype": "torch.float16"
},
"model.layers.0.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.0.mlp.down_proj.trellis": {
"shape": [
896,
512,
64
],
"n_bytes": 58720256,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.1.input_layernorm": {
"stored_tensors": {
"model.layers.1.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.1.self_attn.q_proj": {
"stored_tensors": {
"model.layers.1.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.1.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.1.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.1.self_attn.k_proj": {
"stored_tensors": {
"model.layers.1.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.1.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.1.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.1.self_attn.v_proj": {
"stored_tensors": {
"model.layers.1.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.1.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.1.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.1.self_attn.o_proj": {
"stored_tensors": {
"model.layers.1.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.1.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.1.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.1.post_attention_layernorm": {
"stored_tensors": {
"model.layers.1.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.1.mlp.up_proj": {
"stored_tensors": {
"model.layers.1.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.1.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.1.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.1.mlp.gate_proj": {
"stored_tensors": {
"model.layers.1.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.1.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.1.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.1.mlp.down_proj": {
"stored_tensors": {
"model.layers.1.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.1.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.1.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.2.input_layernorm": {
"stored_tensors": {
"model.layers.2.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.2.self_attn.q_proj": {
"stored_tensors": {
"model.layers.2.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.2.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.2.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.2.self_attn.k_proj": {
"stored_tensors": {
"model.layers.2.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.2.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.2.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.2.self_attn.v_proj": {
"stored_tensors": {
"model.layers.2.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.2.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.2.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.2.self_attn.o_proj": {
"stored_tensors": {
"model.layers.2.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.2.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.2.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.2.post_attention_layernorm": {
"stored_tensors": {
"model.layers.2.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.2.mlp.up_proj": {
"stored_tensors": {
"model.layers.2.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.2.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.2.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.2.mlp.gate_proj": {
"stored_tensors": {
"model.layers.2.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.2.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.2.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.2.mlp.down_proj": {
"stored_tensors": {
"model.layers.2.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.2.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.2.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.3.input_layernorm": {
"stored_tensors": {
"model.layers.3.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.3.self_attn.q_proj": {
"stored_tensors": {
"model.layers.3.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.3.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.3.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.3.self_attn.k_proj": {
"stored_tensors": {
"model.layers.3.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.3.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.3.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.3.self_attn.v_proj": {
"stored_tensors": {
"model.layers.3.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.3.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.3.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.3.self_attn.o_proj": {
"stored_tensors": {
"model.layers.3.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.3.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.3.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.3.post_attention_layernorm": {
"stored_tensors": {
"model.layers.3.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.3.mlp.up_proj": {
"stored_tensors": {
"model.layers.3.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.3.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.3.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.3.mlp.gate_proj": {
"stored_tensors": {
"model.layers.3.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.3.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.3.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.3.mlp.down_proj": {
"stored_tensors": {
"model.layers.3.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.3.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.3.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.4.input_layernorm": {
"stored_tensors": {
"model.layers.4.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.4.self_attn.q_proj": {
"stored_tensors": {
"model.layers.4.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.4.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.4.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.4.self_attn.k_proj": {
"stored_tensors": {
"model.layers.4.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.4.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.4.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.4.self_attn.v_proj": {
"stored_tensors": {
"model.layers.4.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.4.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.4.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.4.self_attn.o_proj": {
"stored_tensors": {
"model.layers.4.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.4.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.4.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.4.post_attention_layernorm": {
"stored_tensors": {
"model.layers.4.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.4.mlp.up_proj": {
"stored_tensors": {
"model.layers.4.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.4.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.4.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.4.mlp.gate_proj": {
"stored_tensors": {
"model.layers.4.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.4.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.4.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.4.mlp.down_proj": {
"stored_tensors": {
"model.layers.4.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.4.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.4.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.5.input_layernorm": {
"stored_tensors": {
"model.layers.5.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.5.self_attn.q_proj": {
"stored_tensors": {
"model.layers.5.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.5.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.5.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.5.self_attn.k_proj": {
"stored_tensors": {
"model.layers.5.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.5.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.5.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.5.self_attn.v_proj": {
"stored_tensors": {
"model.layers.5.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.5.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.5.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.5.self_attn.o_proj": {
"stored_tensors": {
"model.layers.5.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.5.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.5.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.5.post_attention_layernorm": {
"stored_tensors": {
"model.layers.5.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.5.mlp.up_proj": {
"stored_tensors": {
"model.layers.5.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.5.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.5.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.5.mlp.gate_proj": {
"stored_tensors": {
"model.layers.5.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.5.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.5.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.5.mlp.down_proj": {
"stored_tensors": {
"model.layers.5.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.5.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.5.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.6.post_attention_layernorm": {
"stored_tensors": {
"model.layers.6.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.6.mlp.up_proj": {
"stored_tensors": {
"model.layers.6.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.6.mlp.up_proj.svh": {
"shape": [
14336
],
"n_bytes": 28672,
"dtype": "torch.float16"
},
"model.layers.6.mlp.up_proj.trellis": {
"shape": [
512,
896,
64
],
"n_bytes": 58720256,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.6.mlp.gate_proj": {
"stored_tensors": {
"model.layers.6.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.6.mlp.gate_proj.svh": {
"shape": [
14336
],
"n_bytes": 28672,
"dtype": "torch.float16"
},
"model.layers.6.mlp.gate_proj.trellis": {
"shape": [
512,
896,
64
],
"n_bytes": 58720256,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.6.mlp.down_proj": {
"stored_tensors": {
"model.layers.6.mlp.down_proj.suh": {
"shape": [
14336
],
"n_bytes": 28672,
"dtype": "torch.float16"
},
"model.layers.6.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.6.mlp.down_proj.trellis": {
"shape": [
896,
512,
64
],
"n_bytes": 58720256,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.7.post_attention_layernorm": {
"stored_tensors": {
"model.layers.7.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.7.mlp.up_proj": {
"stored_tensors": {
"model.layers.7.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.7.mlp.up_proj.svh": {
"shape": [
14336
],
"n_bytes": 28672,
"dtype": "torch.float16"
},
"model.layers.7.mlp.up_proj.trellis": {
"shape": [
512,
896,
64
],
"n_bytes": 58720256,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.7.mlp.gate_proj": {
"stored_tensors": {
"model.layers.7.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.7.mlp.gate_proj.svh": {
"shape": [
14336
],
"n_bytes": 28672,
"dtype": "torch.float16"
},
"model.layers.7.mlp.gate_proj.trellis": {
"shape": [
512,
896,
64
],
"n_bytes": 58720256,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.7.mlp.down_proj": {
"stored_tensors": {
"model.layers.7.mlp.down_proj.suh": {
"shape": [
14336
],
"n_bytes": 28672,
"dtype": "torch.float16"
},
"model.layers.7.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.7.mlp.down_proj.trellis": {
"shape": [
896,
512,
64
],
"n_bytes": 58720256,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.8.input_layernorm": {
"stored_tensors": {
"model.layers.8.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.8.self_attn.q_proj": {
"stored_tensors": {
"model.layers.8.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.8.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.8.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.8.self_attn.k_proj": {
"stored_tensors": {
"model.layers.8.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.8.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.8.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.8.self_attn.v_proj": {
"stored_tensors": {
"model.layers.8.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.8.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.8.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.8.self_attn.o_proj": {
"stored_tensors": {
"model.layers.8.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.8.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.8.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.8.post_attention_layernorm": {
"stored_tensors": {
"model.layers.8.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.8.mlp.up_proj": {
"stored_tensors": {
"model.layers.8.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.8.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.8.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.8.mlp.gate_proj": {
"stored_tensors": {
"model.layers.8.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.8.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.8.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.8.mlp.down_proj": {
"stored_tensors": {
"model.layers.8.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.8.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.8.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.9.input_layernorm": {
"stored_tensors": {
"model.layers.9.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.9.self_attn.q_proj": {
"stored_tensors": {
"model.layers.9.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.9.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.9.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.9.self_attn.k_proj": {
"stored_tensors": {
"model.layers.9.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.9.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.9.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.9.self_attn.v_proj": {
"stored_tensors": {
"model.layers.9.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.9.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.9.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.9.self_attn.o_proj": {
"stored_tensors": {
"model.layers.9.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.9.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.9.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.9.post_attention_layernorm": {
"stored_tensors": {
"model.layers.9.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.9.mlp.up_proj": {
"stored_tensors": {
"model.layers.9.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.9.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.9.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.9.mlp.gate_proj": {
"stored_tensors": {
"model.layers.9.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.9.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.9.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.9.mlp.down_proj": {
"stored_tensors": {
"model.layers.9.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.9.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.9.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.10.input_layernorm": {
"stored_tensors": {
"model.layers.10.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.10.self_attn.q_proj": {
"stored_tensors": {
"model.layers.10.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.10.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.10.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.10.self_attn.k_proj": {
"stored_tensors": {
"model.layers.10.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.10.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.10.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.10.self_attn.v_proj": {
"stored_tensors": {
"model.layers.10.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.10.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.10.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.10.self_attn.o_proj": {
"stored_tensors": {
"model.layers.10.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.10.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.10.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.10.post_attention_layernorm": {
"stored_tensors": {
"model.layers.10.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.10.mlp.up_proj": {
"stored_tensors": {
"model.layers.10.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.10.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.10.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.10.mlp.gate_proj": {
"stored_tensors": {
"model.layers.10.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.10.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.10.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.10.mlp.down_proj": {
"stored_tensors": {
"model.layers.10.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.10.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.10.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.11.post_attention_layernorm": {
"stored_tensors": {
"model.layers.11.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.11.mlp.up_proj": {
"stored_tensors": {
"model.layers.11.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.11.mlp.up_proj.svh": {
"shape": [
17920
],
"n_bytes": 35840,
"dtype": "torch.float16"
},
"model.layers.11.mlp.up_proj.trellis": {
"shape": [
512,
1120,
64
],
"n_bytes": 73400320,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.11.mlp.gate_proj": {
"stored_tensors": {
"model.layers.11.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.11.mlp.gate_proj.svh": {
"shape": [
17920
],
"n_bytes": 35840,
"dtype": "torch.float16"
},
"model.layers.11.mlp.gate_proj.trellis": {
"shape": [
512,
1120,
64
],
"n_bytes": 73400320,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.11.mlp.down_proj": {
"stored_tensors": {
"model.layers.11.mlp.down_proj.suh": {
"shape": [
17920
],
"n_bytes": 35840,
"dtype": "torch.float16"
},
"model.layers.11.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.11.mlp.down_proj.trellis": {
"shape": [
1120,
512,
64
],
"n_bytes": 73400320,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.12.input_layernorm": {
"stored_tensors": {
"model.layers.12.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.12.self_attn.q_proj": {
"stored_tensors": {
"model.layers.12.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.12.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.12.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.12.self_attn.k_proj": {
"stored_tensors": {
"model.layers.12.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.12.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.12.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.12.self_attn.v_proj": {
"stored_tensors": {
"model.layers.12.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.12.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.12.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.12.self_attn.o_proj": {
"stored_tensors": {
"model.layers.12.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.12.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.12.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.12.post_attention_layernorm": {
"stored_tensors": {
"model.layers.12.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.12.mlp.up_proj": {
"stored_tensors": {
"model.layers.12.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.12.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.12.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.12.mlp.gate_proj": {
"stored_tensors": {
"model.layers.12.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.12.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.12.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.12.mlp.down_proj": {
"stored_tensors": {
"model.layers.12.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.12.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.12.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.13.input_layernorm": {
"stored_tensors": {
"model.layers.13.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.13.self_attn.q_proj": {
"stored_tensors": {
"model.layers.13.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.13.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.13.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.13.self_attn.k_proj": {
"stored_tensors": {
"model.layers.13.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.13.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.13.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.13.self_attn.v_proj": {
"stored_tensors": {
"model.layers.13.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.13.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.13.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.13.self_attn.o_proj": {
"stored_tensors": {
"model.layers.13.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.13.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.13.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.13.post_attention_layernorm": {
"stored_tensors": {
"model.layers.13.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.13.mlp.up_proj": {
"stored_tensors": {
"model.layers.13.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.13.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.13.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.13.mlp.gate_proj": {
"stored_tensors": {
"model.layers.13.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.13.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.13.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.13.mlp.down_proj": {
"stored_tensors": {
"model.layers.13.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.13.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.13.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.14.input_layernorm": {
"stored_tensors": {
"model.layers.14.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.14.self_attn.q_proj": {
"stored_tensors": {
"model.layers.14.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.14.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.14.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.14.self_attn.k_proj": {
"stored_tensors": {
"model.layers.14.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.14.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.14.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.14.self_attn.v_proj": {
"stored_tensors": {
"model.layers.14.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.14.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.14.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.14.self_attn.o_proj": {
"stored_tensors": {
"model.layers.14.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.14.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.14.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.14.post_attention_layernorm": {
"stored_tensors": {
"model.layers.14.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.14.mlp.up_proj": {
"stored_tensors": {
"model.layers.14.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.14.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.14.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.14.mlp.gate_proj": {
"stored_tensors": {
"model.layers.14.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.14.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.14.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.14.mlp.down_proj": {
"stored_tensors": {
"model.layers.14.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.14.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.14.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.15.input_layernorm": {
"stored_tensors": {
"model.layers.15.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.15.self_attn.q_proj": {
"stored_tensors": {
"model.layers.15.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.15.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.15.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.15.self_attn.k_proj": {
"stored_tensors": {
"model.layers.15.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.15.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.15.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.15.self_attn.v_proj": {
"stored_tensors": {
"model.layers.15.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.15.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.15.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.15.self_attn.o_proj": {
"stored_tensors": {
"model.layers.15.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.15.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.15.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.15.post_attention_layernorm": {
"stored_tensors": {
"model.layers.15.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.15.mlp.up_proj": {
"stored_tensors": {
"model.layers.15.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.15.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.15.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.15.mlp.gate_proj": {
"stored_tensors": {
"model.layers.15.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.15.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.15.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.15.mlp.down_proj": {
"stored_tensors": {
"model.layers.15.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.15.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.15.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.16.input_layernorm": {
"stored_tensors": {
"model.layers.16.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.16.self_attn.q_proj": {
"stored_tensors": {
"model.layers.16.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.16.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.16.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.16.self_attn.k_proj": {
"stored_tensors": {
"model.layers.16.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.16.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.16.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.16.self_attn.v_proj": {
"stored_tensors": {
"model.layers.16.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.16.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.16.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.16.self_attn.o_proj": {
"stored_tensors": {
"model.layers.16.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.16.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.16.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.16.post_attention_layernorm": {
"stored_tensors": {
"model.layers.16.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.16.mlp.up_proj": {
"stored_tensors": {
"model.layers.16.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.16.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.16.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.16.mlp.gate_proj": {
"stored_tensors": {
"model.layers.16.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.16.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.16.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.16.mlp.down_proj": {
"stored_tensors": {
"model.layers.16.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.16.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.16.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.17.input_layernorm": {
"stored_tensors": {
"model.layers.17.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.17.self_attn.q_proj": {
"stored_tensors": {
"model.layers.17.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.17.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.17.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.17.self_attn.k_proj": {
"stored_tensors": {
"model.layers.17.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.17.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.17.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.17.self_attn.v_proj": {
"stored_tensors": {
"model.layers.17.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.17.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.17.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.17.self_attn.o_proj": {
"stored_tensors": {
"model.layers.17.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.17.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.17.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.17.post_attention_layernorm": {
"stored_tensors": {
"model.layers.17.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.17.mlp.up_proj": {
"stored_tensors": {
"model.layers.17.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.17.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.17.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.17.mlp.gate_proj": {
"stored_tensors": {
"model.layers.17.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.17.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.17.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.17.mlp.down_proj": {
"stored_tensors": {
"model.layers.17.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.17.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.17.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.18.input_layernorm": {
"stored_tensors": {
"model.layers.18.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.18.self_attn.q_proj": {
"stored_tensors": {
"model.layers.18.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.18.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.18.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.18.self_attn.k_proj": {
"stored_tensors": {
"model.layers.18.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.18.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.18.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.18.self_attn.v_proj": {
"stored_tensors": {
"model.layers.18.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.18.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.18.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.18.self_attn.o_proj": {
"stored_tensors": {
"model.layers.18.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.18.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.18.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.18.post_attention_layernorm": {
"stored_tensors": {
"model.layers.18.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.18.mlp.up_proj": {
"stored_tensors": {
"model.layers.18.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.18.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.18.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.18.mlp.gate_proj": {
"stored_tensors": {
"model.layers.18.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.18.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.18.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.18.mlp.down_proj": {
"stored_tensors": {
"model.layers.18.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.18.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.18.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.19.input_layernorm": {
"stored_tensors": {
"model.layers.19.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.19.self_attn.q_proj": {
"stored_tensors": {
"model.layers.19.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.19.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.19.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.19.self_attn.k_proj": {
"stored_tensors": {
"model.layers.19.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.19.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.19.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.19.self_attn.v_proj": {
"stored_tensors": {
"model.layers.19.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.19.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.19.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.19.self_attn.o_proj": {
"stored_tensors": {
"model.layers.19.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.19.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.19.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.19.post_attention_layernorm": {
"stored_tensors": {
"model.layers.19.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.19.mlp.up_proj": {
"stored_tensors": {
"model.layers.19.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.19.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.19.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.19.mlp.gate_proj": {
"stored_tensors": {
"model.layers.19.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.19.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.19.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.19.mlp.down_proj": {
"stored_tensors": {
"model.layers.19.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.19.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.19.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.20.input_layernorm": {
"stored_tensors": {
"model.layers.20.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.20.self_attn.q_proj": {
"stored_tensors": {
"model.layers.20.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.20.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.20.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.20.self_attn.k_proj": {
"stored_tensors": {
"model.layers.20.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.20.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.20.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.20.self_attn.v_proj": {
"stored_tensors": {
"model.layers.20.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.20.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.20.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.20.self_attn.o_proj": {
"stored_tensors": {
"model.layers.20.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.20.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.20.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.20.post_attention_layernorm": {
"stored_tensors": {
"model.layers.20.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.20.mlp.up_proj": {
"stored_tensors": {
"model.layers.20.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.20.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.20.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.20.mlp.gate_proj": {
"stored_tensors": {
"model.layers.20.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.20.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.20.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.20.mlp.down_proj": {
"stored_tensors": {
"model.layers.20.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.20.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.20.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.21.input_layernorm": {
"stored_tensors": {
"model.layers.21.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.21.self_attn.q_proj": {
"stored_tensors": {
"model.layers.21.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.21.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.21.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.21.self_attn.k_proj": {
"stored_tensors": {
"model.layers.21.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.21.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.21.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.21.self_attn.v_proj": {
"stored_tensors": {
"model.layers.21.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.21.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.21.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.21.self_attn.o_proj": {
"stored_tensors": {
"model.layers.21.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.21.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.21.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.21.post_attention_layernorm": {
"stored_tensors": {
"model.layers.21.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.21.mlp.up_proj": {
"stored_tensors": {
"model.layers.21.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.21.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.21.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.21.mlp.gate_proj": {
"stored_tensors": {
"model.layers.21.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.21.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.21.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.21.mlp.down_proj": {
"stored_tensors": {
"model.layers.21.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.21.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.21.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.22.input_layernorm": {
"stored_tensors": {
"model.layers.22.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.22.self_attn.q_proj": {
"stored_tensors": {
"model.layers.22.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.22.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.22.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.22.self_attn.k_proj": {
"stored_tensors": {
"model.layers.22.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.22.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.22.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.22.self_attn.v_proj": {
"stored_tensors": {
"model.layers.22.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.22.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.22.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.22.self_attn.o_proj": {
"stored_tensors": {
"model.layers.22.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.22.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.22.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.22.post_attention_layernorm": {
"stored_tensors": {
"model.layers.22.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.22.mlp.up_proj": {
"stored_tensors": {
"model.layers.22.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.22.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.22.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.22.mlp.gate_proj": {
"stored_tensors": {
"model.layers.22.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.22.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.22.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.22.mlp.down_proj": {
"stored_tensors": {
"model.layers.22.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.22.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.22.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.23.input_layernorm": {
"stored_tensors": {
"model.layers.23.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.23.self_attn.q_proj": {
"stored_tensors": {
"model.layers.23.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.23.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.23.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.23.self_attn.k_proj": {
"stored_tensors": {
"model.layers.23.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.23.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.23.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.23.self_attn.v_proj": {
"stored_tensors": {
"model.layers.23.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.23.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.23.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.23.self_attn.o_proj": {
"stored_tensors": {
"model.layers.23.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.23.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.23.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.23.post_attention_layernorm": {
"stored_tensors": {
"model.layers.23.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.23.mlp.up_proj": {
"stored_tensors": {
"model.layers.23.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.23.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.23.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.23.mlp.gate_proj": {
"stored_tensors": {
"model.layers.23.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.23.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.23.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.23.mlp.down_proj": {
"stored_tensors": {
"model.layers.23.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.23.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.23.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.24.input_layernorm": {
"stored_tensors": {
"model.layers.24.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.24.self_attn.q_proj": {
"stored_tensors": {
"model.layers.24.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.24.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.24.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.24.self_attn.k_proj": {
"stored_tensors": {
"model.layers.24.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.24.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.24.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.24.self_attn.v_proj": {
"stored_tensors": {
"model.layers.24.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.24.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.24.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.24.self_attn.o_proj": {
"stored_tensors": {
"model.layers.24.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.24.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.24.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.24.post_attention_layernorm": {
"stored_tensors": {
"model.layers.24.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.24.mlp.up_proj": {
"stored_tensors": {
"model.layers.24.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.24.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.24.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.24.mlp.gate_proj": {
"stored_tensors": {
"model.layers.24.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.24.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.24.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.24.mlp.down_proj": {
"stored_tensors": {
"model.layers.24.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.24.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.24.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.25.input_layernorm": {
"stored_tensors": {
"model.layers.25.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.25.self_attn.q_proj": {
"stored_tensors": {
"model.layers.25.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.25.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.25.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.25.self_attn.k_proj": {
"stored_tensors": {
"model.layers.25.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.25.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.25.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.25.self_attn.v_proj": {
"stored_tensors": {
"model.layers.25.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.25.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.25.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.25.self_attn.o_proj": {
"stored_tensors": {
"model.layers.25.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.25.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.25.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.25.post_attention_layernorm": {
"stored_tensors": {
"model.layers.25.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.25.mlp.up_proj": {
"stored_tensors": {
"model.layers.25.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.25.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.25.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.25.mlp.gate_proj": {
"stored_tensors": {
"model.layers.25.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.25.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.25.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.25.mlp.down_proj": {
"stored_tensors": {
"model.layers.25.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.25.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.25.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.26.input_layernorm": {
"stored_tensors": {
"model.layers.26.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.26.self_attn.q_proj": {
"stored_tensors": {
"model.layers.26.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.26.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.26.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.26.self_attn.k_proj": {
"stored_tensors": {
"model.layers.26.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.26.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.26.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.26.self_attn.v_proj": {
"stored_tensors": {
"model.layers.26.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.26.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.26.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.26.self_attn.o_proj": {
"stored_tensors": {
"model.layers.26.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.26.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.26.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.26.post_attention_layernorm": {
"stored_tensors": {
"model.layers.26.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.26.mlp.up_proj": {
"stored_tensors": {
"model.layers.26.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.26.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.26.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.26.mlp.gate_proj": {
"stored_tensors": {
"model.layers.26.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.26.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.26.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.26.mlp.down_proj": {
"stored_tensors": {
"model.layers.26.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.26.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.26.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.27.input_layernorm": {
"stored_tensors": {
"model.layers.27.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.27.self_attn.q_proj": {
"stored_tensors": {
"model.layers.27.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.27.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.27.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.27.self_attn.k_proj": {
"stored_tensors": {
"model.layers.27.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.27.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.27.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.27.self_attn.v_proj": {
"stored_tensors": {
"model.layers.27.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.27.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.27.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.27.self_attn.o_proj": {
"stored_tensors": {
"model.layers.27.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.27.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.27.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.27.post_attention_layernorm": {
"stored_tensors": {
"model.layers.27.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.27.mlp.up_proj": {
"stored_tensors": {
"model.layers.27.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.27.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.27.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.27.mlp.gate_proj": {
"stored_tensors": {
"model.layers.27.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.27.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.27.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.27.mlp.down_proj": {
"stored_tensors": {
"model.layers.27.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.27.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.27.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.28.input_layernorm": {
"stored_tensors": {
"model.layers.28.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.28.self_attn.q_proj": {
"stored_tensors": {
"model.layers.28.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.28.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.28.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.28.self_attn.k_proj": {
"stored_tensors": {
"model.layers.28.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.28.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.28.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.28.self_attn.v_proj": {
"stored_tensors": {
"model.layers.28.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.28.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.28.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.28.self_attn.o_proj": {
"stored_tensors": {
"model.layers.28.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.28.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.28.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.28.post_attention_layernorm": {
"stored_tensors": {
"model.layers.28.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.28.mlp.up_proj": {
"stored_tensors": {
"model.layers.28.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.28.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.28.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.28.mlp.gate_proj": {
"stored_tensors": {
"model.layers.28.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.28.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.28.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.28.mlp.down_proj": {
"stored_tensors": {
"model.layers.28.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.28.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.28.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.29.input_layernorm": {
"stored_tensors": {
"model.layers.29.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.29.self_attn.q_proj": {
"stored_tensors": {
"model.layers.29.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.29.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.29.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.29.self_attn.k_proj": {
"stored_tensors": {
"model.layers.29.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.29.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.29.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.29.self_attn.v_proj": {
"stored_tensors": {
"model.layers.29.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.29.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.29.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.29.self_attn.o_proj": {
"stored_tensors": {
"model.layers.29.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.29.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.29.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.29.post_attention_layernorm": {
"stored_tensors": {
"model.layers.29.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.29.mlp.up_proj": {
"stored_tensors": {
"model.layers.29.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.29.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.29.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.29.mlp.gate_proj": {
"stored_tensors": {
"model.layers.29.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.29.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.29.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.29.mlp.down_proj": {
"stored_tensors": {
"model.layers.29.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.29.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.29.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.30.input_layernorm": {
"stored_tensors": {
"model.layers.30.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.30.self_attn.q_proj": {
"stored_tensors": {
"model.layers.30.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.30.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.30.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.30.self_attn.k_proj": {
"stored_tensors": {
"model.layers.30.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.30.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.30.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.30.self_attn.v_proj": {
"stored_tensors": {
"model.layers.30.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.30.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.30.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.30.self_attn.o_proj": {
"stored_tensors": {
"model.layers.30.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.30.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.30.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.30.post_attention_layernorm": {
"stored_tensors": {
"model.layers.30.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.30.mlp.up_proj": {
"stored_tensors": {
"model.layers.30.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.30.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.30.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.30.mlp.gate_proj": {
"stored_tensors": {
"model.layers.30.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.30.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.30.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.30.mlp.down_proj": {
"stored_tensors": {
"model.layers.30.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.30.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.30.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.31.input_layernorm": {
"stored_tensors": {
"model.layers.31.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.31.self_attn.q_proj": {
"stored_tensors": {
"model.layers.31.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.31.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.31.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.31.self_attn.k_proj": {
"stored_tensors": {
"model.layers.31.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.31.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.31.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.31.self_attn.v_proj": {
"stored_tensors": {
"model.layers.31.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.31.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.31.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.31.self_attn.o_proj": {
"stored_tensors": {
"model.layers.31.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.31.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.31.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.31.post_attention_layernorm": {
"stored_tensors": {
"model.layers.31.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.31.mlp.up_proj": {
"stored_tensors": {
"model.layers.31.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.31.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.31.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.31.mlp.gate_proj": {
"stored_tensors": {
"model.layers.31.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.31.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.31.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.31.mlp.down_proj": {
"stored_tensors": {
"model.layers.31.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.31.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.31.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.32.input_layernorm": {
"stored_tensors": {
"model.layers.32.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.32.self_attn.q_proj": {
"stored_tensors": {
"model.layers.32.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.32.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.32.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.32.self_attn.k_proj": {
"stored_tensors": {
"model.layers.32.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.32.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.32.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.32.self_attn.v_proj": {
"stored_tensors": {
"model.layers.32.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.32.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.32.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.32.self_attn.o_proj": {
"stored_tensors": {
"model.layers.32.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.32.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.32.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.32.post_attention_layernorm": {
"stored_tensors": {
"model.layers.32.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.32.mlp.up_proj": {
"stored_tensors": {
"model.layers.32.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.32.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.32.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.32.mlp.gate_proj": {
"stored_tensors": {
"model.layers.32.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.32.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.32.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.32.mlp.down_proj": {
"stored_tensors": {
"model.layers.32.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.32.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.32.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.33.input_layernorm": {
"stored_tensors": {
"model.layers.33.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.33.self_attn.q_proj": {
"stored_tensors": {
"model.layers.33.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.33.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.33.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.33.self_attn.k_proj": {
"stored_tensors": {
"model.layers.33.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.33.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.33.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.33.self_attn.v_proj": {
"stored_tensors": {
"model.layers.33.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.33.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.33.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.33.self_attn.o_proj": {
"stored_tensors": {
"model.layers.33.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.33.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.33.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.33.post_attention_layernorm": {
"stored_tensors": {
"model.layers.33.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.33.mlp.up_proj": {
"stored_tensors": {
"model.layers.33.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.33.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.33.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.33.mlp.gate_proj": {
"stored_tensors": {
"model.layers.33.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.33.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.33.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.33.mlp.down_proj": {
"stored_tensors": {
"model.layers.33.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.33.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.33.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.34.input_layernorm": {
"stored_tensors": {
"model.layers.34.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.34.self_attn.q_proj": {
"stored_tensors": {
"model.layers.34.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.34.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.34.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.34.self_attn.k_proj": {
"stored_tensors": {
"model.layers.34.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.34.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.34.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.34.self_attn.v_proj": {
"stored_tensors": {
"model.layers.34.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.34.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.34.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.34.self_attn.o_proj": {
"stored_tensors": {
"model.layers.34.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.34.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.34.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.34.post_attention_layernorm": {
"stored_tensors": {
"model.layers.34.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.34.mlp.up_proj": {
"stored_tensors": {
"model.layers.34.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.34.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.34.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.34.mlp.gate_proj": {
"stored_tensors": {
"model.layers.34.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.34.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.34.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.34.mlp.down_proj": {
"stored_tensors": {
"model.layers.34.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.34.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.34.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.35.input_layernorm": {
"stored_tensors": {
"model.layers.35.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.35.self_attn.q_proj": {
"stored_tensors": {
"model.layers.35.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.35.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.35.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.35.self_attn.k_proj": {
"stored_tensors": {
"model.layers.35.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.35.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.35.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.35.self_attn.v_proj": {
"stored_tensors": {
"model.layers.35.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.35.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.35.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.35.self_attn.o_proj": {
"stored_tensors": {
"model.layers.35.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.35.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.35.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.35.post_attention_layernorm": {
"stored_tensors": {
"model.layers.35.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.35.mlp.up_proj": {
"stored_tensors": {
"model.layers.35.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.35.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.35.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.35.mlp.gate_proj": {
"stored_tensors": {
"model.layers.35.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.35.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.35.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.35.mlp.down_proj": {
"stored_tensors": {
"model.layers.35.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.35.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.35.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.36.input_layernorm": {
"stored_tensors": {
"model.layers.36.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.36.self_attn.q_proj": {
"stored_tensors": {
"model.layers.36.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.36.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.36.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.36.self_attn.k_proj": {
"stored_tensors": {
"model.layers.36.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.36.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.36.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.36.self_attn.v_proj": {
"stored_tensors": {
"model.layers.36.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.36.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.36.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.36.self_attn.o_proj": {
"stored_tensors": {
"model.layers.36.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.36.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.36.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.36.post_attention_layernorm": {
"stored_tensors": {
"model.layers.36.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.36.mlp.up_proj": {
"stored_tensors": {
"model.layers.36.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.36.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.36.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.36.mlp.gate_proj": {
"stored_tensors": {
"model.layers.36.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.36.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.36.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.36.mlp.down_proj": {
"stored_tensors": {
"model.layers.36.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.36.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.36.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.37.input_layernorm": {
"stored_tensors": {
"model.layers.37.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.37.self_attn.q_proj": {
"stored_tensors": {
"model.layers.37.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.37.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.37.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.37.self_attn.k_proj": {
"stored_tensors": {
"model.layers.37.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.37.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.37.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.37.self_attn.v_proj": {
"stored_tensors": {
"model.layers.37.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.37.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.37.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.37.self_attn.o_proj": {
"stored_tensors": {
"model.layers.37.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.37.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.37.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.37.post_attention_layernorm": {
"stored_tensors": {
"model.layers.37.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.37.mlp.up_proj": {
"stored_tensors": {
"model.layers.37.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.37.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.37.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.37.mlp.gate_proj": {
"stored_tensors": {
"model.layers.37.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.37.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.37.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.37.mlp.down_proj": {
"stored_tensors": {
"model.layers.37.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.37.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.37.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.38.input_layernorm": {
"stored_tensors": {
"model.layers.38.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.38.self_attn.q_proj": {
"stored_tensors": {
"model.layers.38.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.38.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.38.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.38.self_attn.k_proj": {
"stored_tensors": {
"model.layers.38.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.38.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.38.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.38.self_attn.v_proj": {
"stored_tensors": {
"model.layers.38.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.38.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.38.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.38.self_attn.o_proj": {
"stored_tensors": {
"model.layers.38.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.38.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.38.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.38.post_attention_layernorm": {
"stored_tensors": {
"model.layers.38.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.38.mlp.up_proj": {
"stored_tensors": {
"model.layers.38.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.38.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.38.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.38.mlp.gate_proj": {
"stored_tensors": {
"model.layers.38.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.38.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.38.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.38.mlp.down_proj": {
"stored_tensors": {
"model.layers.38.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.38.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.38.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.39.input_layernorm": {
"stored_tensors": {
"model.layers.39.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.39.self_attn.q_proj": {
"stored_tensors": {
"model.layers.39.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.39.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.39.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.39.self_attn.k_proj": {
"stored_tensors": {
"model.layers.39.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.39.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.39.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.39.self_attn.v_proj": {
"stored_tensors": {
"model.layers.39.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.39.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.39.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.39.self_attn.o_proj": {
"stored_tensors": {
"model.layers.39.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.39.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.39.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.39.post_attention_layernorm": {
"stored_tensors": {
"model.layers.39.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.39.mlp.up_proj": {
"stored_tensors": {
"model.layers.39.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.39.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.39.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.39.mlp.gate_proj": {
"stored_tensors": {
"model.layers.39.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.39.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.39.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.39.mlp.down_proj": {
"stored_tensors": {
"model.layers.39.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.39.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.39.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.40.input_layernorm": {
"stored_tensors": {
"model.layers.40.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.40.self_attn.q_proj": {
"stored_tensors": {
"model.layers.40.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.40.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.40.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.40.self_attn.k_proj": {
"stored_tensors": {
"model.layers.40.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.40.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.40.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.40.self_attn.v_proj": {
"stored_tensors": {
"model.layers.40.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.40.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.40.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.40.self_attn.o_proj": {
"stored_tensors": {
"model.layers.40.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.40.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.40.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.40.post_attention_layernorm": {
"stored_tensors": {
"model.layers.40.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.40.mlp.up_proj": {
"stored_tensors": {
"model.layers.40.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.40.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.40.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.40.mlp.gate_proj": {
"stored_tensors": {
"model.layers.40.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.40.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.40.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.40.mlp.down_proj": {
"stored_tensors": {
"model.layers.40.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.40.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.40.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.41.input_layernorm": {
"stored_tensors": {
"model.layers.41.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.41.self_attn.q_proj": {
"stored_tensors": {
"model.layers.41.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.41.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.41.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.41.self_attn.k_proj": {
"stored_tensors": {
"model.layers.41.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.41.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.41.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.41.self_attn.v_proj": {
"stored_tensors": {
"model.layers.41.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.41.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.41.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.41.self_attn.o_proj": {
"stored_tensors": {
"model.layers.41.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.41.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.41.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.41.post_attention_layernorm": {
"stored_tensors": {
"model.layers.41.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.41.mlp.up_proj": {
"stored_tensors": {
"model.layers.41.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.41.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.41.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.41.mlp.gate_proj": {
"stored_tensors": {
"model.layers.41.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.41.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.41.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.41.mlp.down_proj": {
"stored_tensors": {
"model.layers.41.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.41.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.41.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.42.post_attention_layernorm": {
"stored_tensors": {
"model.layers.42.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.42.mlp.up_proj": {
"stored_tensors": {
"model.layers.42.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.42.mlp.up_proj.svh": {
"shape": [
7168
],
"n_bytes": 14336,
"dtype": "torch.float16"
},
"model.layers.42.mlp.up_proj.trellis": {
"shape": [
512,
448,
64
],
"n_bytes": 29360128,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.42.mlp.gate_proj": {
"stored_tensors": {
"model.layers.42.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.42.mlp.gate_proj.svh": {
"shape": [
7168
],
"n_bytes": 14336,
"dtype": "torch.float16"
},
"model.layers.42.mlp.gate_proj.trellis": {
"shape": [
512,
448,
64
],
"n_bytes": 29360128,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.42.mlp.down_proj": {
"stored_tensors": {
"model.layers.42.mlp.down_proj.suh": {
"shape": [
7168
],
"n_bytes": 14336,
"dtype": "torch.float16"
},
"model.layers.42.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.42.mlp.down_proj.trellis": {
"shape": [
448,
512,
64
],
"n_bytes": 29360128,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.43.post_attention_layernorm": {
"stored_tensors": {
"model.layers.43.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.43.mlp.up_proj": {
"stored_tensors": {
"model.layers.43.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.43.mlp.up_proj.svh": {
"shape": [
14336
],
"n_bytes": 28672,
"dtype": "torch.float16"
},
"model.layers.43.mlp.up_proj.trellis": {
"shape": [
512,
896,
64
],
"n_bytes": 58720256,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.43.mlp.gate_proj": {
"stored_tensors": {
"model.layers.43.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.43.mlp.gate_proj.svh": {
"shape": [
14336
],
"n_bytes": 28672,
"dtype": "torch.float16"
},
"model.layers.43.mlp.gate_proj.trellis": {
"shape": [
512,
896,
64
],
"n_bytes": 58720256,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.43.mlp.down_proj": {
"stored_tensors": {
"model.layers.43.mlp.down_proj.suh": {
"shape": [
14336
],
"n_bytes": 28672,
"dtype": "torch.float16"
},
"model.layers.43.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.43.mlp.down_proj.trellis": {
"shape": [
896,
512,
64
],
"n_bytes": 58720256,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.44.post_attention_layernorm": {
"stored_tensors": {
"model.layers.44.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.44.mlp.up_proj": {
"stored_tensors": {
"model.layers.44.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.44.mlp.up_proj.svh": {
"shape": [
14336
],
"n_bytes": 28672,
"dtype": "torch.float16"
},
"model.layers.44.mlp.up_proj.trellis": {
"shape": [
512,
896,
64
],
"n_bytes": 58720256,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.44.mlp.gate_proj": {
"stored_tensors": {
"model.layers.44.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.44.mlp.gate_proj.svh": {
"shape": [
14336
],
"n_bytes": 28672,
"dtype": "torch.float16"
},
"model.layers.44.mlp.gate_proj.trellis": {
"shape": [
512,
896,
64
],
"n_bytes": 58720256,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.44.mlp.down_proj": {
"stored_tensors": {
"model.layers.44.mlp.down_proj.suh": {
"shape": [
14336
],
"n_bytes": 28672,
"dtype": "torch.float16"
},
"model.layers.44.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.44.mlp.down_proj.trellis": {
"shape": [
896,
512,
64
],
"n_bytes": 58720256,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.45.post_attention_layernorm": {
"stored_tensors": {
"model.layers.45.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.45.mlp.up_proj": {
"stored_tensors": {
"model.layers.45.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.45.mlp.up_proj.svh": {
"shape": [
7168
],
"n_bytes": 14336,
"dtype": "torch.float16"
},
"model.layers.45.mlp.up_proj.trellis": {
"shape": [
512,
448,
64
],
"n_bytes": 29360128,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.45.mlp.gate_proj": {
"stored_tensors": {
"model.layers.45.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.45.mlp.gate_proj.svh": {
"shape": [
7168
],
"n_bytes": 14336,
"dtype": "torch.float16"
},
"model.layers.45.mlp.gate_proj.trellis": {
"shape": [
512,
448,
64
],
"n_bytes": 29360128,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.45.mlp.down_proj": {
"stored_tensors": {
"model.layers.45.mlp.down_proj.suh": {
"shape": [
7168
],
"n_bytes": 14336,
"dtype": "torch.float16"
},
"model.layers.45.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.45.mlp.down_proj.trellis": {
"shape": [
448,
512,
64
],
"n_bytes": 29360128,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.46.post_attention_layernorm": {
"stored_tensors": {
"model.layers.46.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.46.mlp.up_proj": {
"stored_tensors": {
"model.layers.46.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.46.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.46.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.46.mlp.gate_proj": {
"stored_tensors": {
"model.layers.46.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.46.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.46.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.46.mlp.down_proj": {
"stored_tensors": {
"model.layers.46.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.46.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.46.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.47.post_attention_layernorm": {
"stored_tensors": {
"model.layers.47.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.47.mlp.up_proj": {
"stored_tensors": {
"model.layers.47.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.47.mlp.up_proj.svh": {
"shape": [
7168
],
"n_bytes": 14336,
"dtype": "torch.float16"
},
"model.layers.47.mlp.up_proj.trellis": {
"shape": [
512,
448,
64
],
"n_bytes": 29360128,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.47.mlp.gate_proj": {
"stored_tensors": {
"model.layers.47.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.47.mlp.gate_proj.svh": {
"shape": [
7168
],
"n_bytes": 14336,
"dtype": "torch.float16"
},
"model.layers.47.mlp.gate_proj.trellis": {
"shape": [
512,
448,
64
],
"n_bytes": 29360128,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.47.mlp.down_proj": {
"stored_tensors": {
"model.layers.47.mlp.down_proj.suh": {
"shape": [
7168
],
"n_bytes": 14336,
"dtype": "torch.float16"
},
"model.layers.47.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.47.mlp.down_proj.trellis": {
"shape": [
448,
512,
64
],
"n_bytes": 29360128,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.48.post_attention_layernorm": {
"stored_tensors": {
"model.layers.48.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.48.mlp.up_proj": {
"stored_tensors": {
"model.layers.48.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.48.mlp.up_proj.svh": {
"shape": [
14336
],
"n_bytes": 28672,
"dtype": "torch.float16"
},
"model.layers.48.mlp.up_proj.trellis": {
"shape": [
512,
896,
64
],
"n_bytes": 58720256,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.48.mlp.gate_proj": {
"stored_tensors": {
"model.layers.48.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.48.mlp.gate_proj.svh": {
"shape": [
14336
],
"n_bytes": 28672,
"dtype": "torch.float16"
},
"model.layers.48.mlp.gate_proj.trellis": {
"shape": [
512,
896,
64
],
"n_bytes": 58720256,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.48.mlp.down_proj": {
"stored_tensors": {
"model.layers.48.mlp.down_proj.suh": {
"shape": [
14336
],
"n_bytes": 28672,
"dtype": "torch.float16"
},
"model.layers.48.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.48.mlp.down_proj.trellis": {
"shape": [
896,
512,
64
],
"n_bytes": 58720256,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.49.post_attention_layernorm": {
"stored_tensors": {
"model.layers.49.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.49.mlp.up_proj": {
"stored_tensors": {
"model.layers.49.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.49.mlp.up_proj.svh": {
"shape": [
7168
],
"n_bytes": 14336,
"dtype": "torch.float16"
},
"model.layers.49.mlp.up_proj.trellis": {
"shape": [
512,
448,
64
],
"n_bytes": 29360128,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.49.mlp.gate_proj": {
"stored_tensors": {
"model.layers.49.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.49.mlp.gate_proj.svh": {
"shape": [
7168
],
"n_bytes": 14336,
"dtype": "torch.float16"
},
"model.layers.49.mlp.gate_proj.trellis": {
"shape": [
512,
448,
64
],
"n_bytes": 29360128,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.49.mlp.down_proj": {
"stored_tensors": {
"model.layers.49.mlp.down_proj.suh": {
"shape": [
7168
],
"n_bytes": 14336,
"dtype": "torch.float16"
},
"model.layers.49.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.49.mlp.down_proj.trellis": {
"shape": [
448,
512,
64
],
"n_bytes": 29360128,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.50.post_attention_layernorm": {
"stored_tensors": {
"model.layers.50.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.50.mlp.up_proj": {
"stored_tensors": {
"model.layers.50.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.50.mlp.up_proj.svh": {
"shape": [
7168
],
"n_bytes": 14336,
"dtype": "torch.float16"
},
"model.layers.50.mlp.up_proj.trellis": {
"shape": [
512,
448,
64
],
"n_bytes": 29360128,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.50.mlp.gate_proj": {
"stored_tensors": {
"model.layers.50.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.50.mlp.gate_proj.svh": {
"shape": [
7168
],
"n_bytes": 14336,
"dtype": "torch.float16"
},
"model.layers.50.mlp.gate_proj.trellis": {
"shape": [
512,
448,
64
],
"n_bytes": 29360128,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.50.mlp.down_proj": {
"stored_tensors": {
"model.layers.50.mlp.down_proj.suh": {
"shape": [
7168
],
"n_bytes": 14336,
"dtype": "torch.float16"
},
"model.layers.50.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.50.mlp.down_proj.trellis": {
"shape": [
448,
512,
64
],
"n_bytes": 29360128,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.51.post_attention_layernorm": {
"stored_tensors": {
"model.layers.51.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.51.mlp.up_proj": {
"stored_tensors": {
"model.layers.51.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.51.mlp.up_proj.svh": {
"shape": [
7168
],
"n_bytes": 14336,
"dtype": "torch.float16"
},
"model.layers.51.mlp.up_proj.trellis": {
"shape": [
512,
448,
64
],
"n_bytes": 29360128,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.51.mlp.gate_proj": {
"stored_tensors": {
"model.layers.51.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.51.mlp.gate_proj.svh": {
"shape": [
7168
],
"n_bytes": 14336,
"dtype": "torch.float16"
},
"model.layers.51.mlp.gate_proj.trellis": {
"shape": [
512,
448,
64
],
"n_bytes": 29360128,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.51.mlp.down_proj": {
"stored_tensors": {
"model.layers.51.mlp.down_proj.suh": {
"shape": [
7168
],
"n_bytes": 14336,
"dtype": "torch.float16"
},
"model.layers.51.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.51.mlp.down_proj.trellis": {
"shape": [
448,
512,
64
],
"n_bytes": 29360128,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.52.input_layernorm": {
"stored_tensors": {
"model.layers.52.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.52.self_attn.q_proj": {
"stored_tensors": {
"model.layers.52.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.52.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.52.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.52.self_attn.k_proj": {
"stored_tensors": {
"model.layers.52.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.52.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.52.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.52.self_attn.v_proj": {
"stored_tensors": {
"model.layers.52.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.52.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.52.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.52.self_attn.o_proj": {
"stored_tensors": {
"model.layers.52.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.52.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.52.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.52.post_attention_layernorm": {
"stored_tensors": {
"model.layers.52.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.52.mlp.up_proj": {
"stored_tensors": {
"model.layers.52.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.52.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.52.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.52.mlp.gate_proj": {
"stored_tensors": {
"model.layers.52.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.52.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.52.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.52.mlp.down_proj": {
"stored_tensors": {
"model.layers.52.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.52.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.52.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.53.post_attention_layernorm": {
"stored_tensors": {
"model.layers.53.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.53.mlp.up_proj": {
"stored_tensors": {
"model.layers.53.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.53.mlp.up_proj.svh": {
"shape": [
7168
],
"n_bytes": 14336,
"dtype": "torch.float16"
},
"model.layers.53.mlp.up_proj.trellis": {
"shape": [
512,
448,
64
],
"n_bytes": 29360128,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.53.mlp.gate_proj": {
"stored_tensors": {
"model.layers.53.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.53.mlp.gate_proj.svh": {
"shape": [
7168
],
"n_bytes": 14336,
"dtype": "torch.float16"
},
"model.layers.53.mlp.gate_proj.trellis": {
"shape": [
512,
448,
64
],
"n_bytes": 29360128,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.53.mlp.down_proj": {
"stored_tensors": {
"model.layers.53.mlp.down_proj.suh": {
"shape": [
7168
],
"n_bytes": 14336,
"dtype": "torch.float16"
},
"model.layers.53.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.53.mlp.down_proj.trellis": {
"shape": [
448,
512,
64
],
"n_bytes": 29360128,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.54.post_attention_layernorm": {
"stored_tensors": {
"model.layers.54.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.54.mlp.up_proj": {
"stored_tensors": {
"model.layers.54.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.54.mlp.up_proj.svh": {
"shape": [
5632
],
"n_bytes": 11264,
"dtype": "torch.float16"
},
"model.layers.54.mlp.up_proj.trellis": {
"shape": [
512,
352,
64
],
"n_bytes": 23068672,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.54.mlp.gate_proj": {
"stored_tensors": {
"model.layers.54.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.54.mlp.gate_proj.svh": {
"shape": [
5632
],
"n_bytes": 11264,
"dtype": "torch.float16"
},
"model.layers.54.mlp.gate_proj.trellis": {
"shape": [
512,
352,
64
],
"n_bytes": 23068672,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.54.mlp.down_proj": {
"stored_tensors": {
"model.layers.54.mlp.down_proj.suh": {
"shape": [
5632
],
"n_bytes": 11264,
"dtype": "torch.float16"
},
"model.layers.54.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.54.mlp.down_proj.trellis": {
"shape": [
352,
512,
64
],
"n_bytes": 23068672,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.55.post_attention_layernorm": {
"stored_tensors": {
"model.layers.55.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.55.mlp.up_proj": {
"stored_tensors": {
"model.layers.55.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.55.mlp.up_proj.svh": {
"shape": [
5632
],
"n_bytes": 11264,
"dtype": "torch.float16"
},
"model.layers.55.mlp.up_proj.trellis": {
"shape": [
512,
352,
64
],
"n_bytes": 23068672,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.55.mlp.gate_proj": {
"stored_tensors": {
"model.layers.55.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.55.mlp.gate_proj.svh": {
"shape": [
5632
],
"n_bytes": 11264,
"dtype": "torch.float16"
},
"model.layers.55.mlp.gate_proj.trellis": {
"shape": [
512,
352,
64
],
"n_bytes": 23068672,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.55.mlp.down_proj": {
"stored_tensors": {
"model.layers.55.mlp.down_proj.suh": {
"shape": [
5632
],
"n_bytes": 11264,
"dtype": "torch.float16"
},
"model.layers.55.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.55.mlp.down_proj.trellis": {
"shape": [
352,
512,
64
],
"n_bytes": 23068672,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.56.post_attention_layernorm": {
"stored_tensors": {
"model.layers.56.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.56.mlp.up_proj": {
"stored_tensors": {
"model.layers.56.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.56.mlp.up_proj.svh": {
"shape": [
7168
],
"n_bytes": 14336,
"dtype": "torch.float16"
},
"model.layers.56.mlp.up_proj.trellis": {
"shape": [
512,
448,
64
],
"n_bytes": 29360128,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.56.mlp.gate_proj": {
"stored_tensors": {
"model.layers.56.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.56.mlp.gate_proj.svh": {
"shape": [
7168
],
"n_bytes": 14336,
"dtype": "torch.float16"
},
"model.layers.56.mlp.gate_proj.trellis": {
"shape": [
512,
448,
64
],
"n_bytes": 29360128,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.56.mlp.down_proj": {
"stored_tensors": {
"model.layers.56.mlp.down_proj.suh": {
"shape": [
7168
],
"n_bytes": 14336,
"dtype": "torch.float16"
},
"model.layers.56.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.56.mlp.down_proj.trellis": {
"shape": [
448,
512,
64
],
"n_bytes": 29360128,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.57.post_attention_layernorm": {
"stored_tensors": {
"model.layers.57.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.57.mlp.up_proj": {
"stored_tensors": {
"model.layers.57.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.57.mlp.up_proj.svh": {
"shape": [
5632
],
"n_bytes": 11264,
"dtype": "torch.float16"
},
"model.layers.57.mlp.up_proj.trellis": {
"shape": [
512,
352,
64
],
"n_bytes": 23068672,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.57.mlp.gate_proj": {
"stored_tensors": {
"model.layers.57.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.57.mlp.gate_proj.svh": {
"shape": [
5632
],
"n_bytes": 11264,
"dtype": "torch.float16"
},
"model.layers.57.mlp.gate_proj.trellis": {
"shape": [
512,
352,
64
],
"n_bytes": 23068672,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.57.mlp.down_proj": {
"stored_tensors": {
"model.layers.57.mlp.down_proj.suh": {
"shape": [
5632
],
"n_bytes": 11264,
"dtype": "torch.float16"
},
"model.layers.57.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.57.mlp.down_proj.trellis": {
"shape": [
352,
512,
64
],
"n_bytes": 23068672,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.58.post_attention_layernorm": {
"stored_tensors": {
"model.layers.58.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.58.mlp.up_proj": {
"stored_tensors": {
"model.layers.58.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.58.mlp.up_proj.svh": {
"shape": [
5632
],
"n_bytes": 11264,
"dtype": "torch.float16"
},
"model.layers.58.mlp.up_proj.trellis": {
"shape": [
512,
352,
64
],
"n_bytes": 23068672,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.58.mlp.gate_proj": {
"stored_tensors": {
"model.layers.58.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.58.mlp.gate_proj.svh": {
"shape": [
5632
],
"n_bytes": 11264,
"dtype": "torch.float16"
},
"model.layers.58.mlp.gate_proj.trellis": {
"shape": [
512,
352,
64
],
"n_bytes": 23068672,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.58.mlp.down_proj": {
"stored_tensors": {
"model.layers.58.mlp.down_proj.suh": {
"shape": [
5632
],
"n_bytes": 11264,
"dtype": "torch.float16"
},
"model.layers.58.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.58.mlp.down_proj.trellis": {
"shape": [
352,
512,
64
],
"n_bytes": 23068672,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.59.post_attention_layernorm": {
"stored_tensors": {
"model.layers.59.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.59.mlp.up_proj": {
"stored_tensors": {
"model.layers.59.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.59.mlp.up_proj.svh": {
"shape": [
5632
],
"n_bytes": 11264,
"dtype": "torch.float16"
},
"model.layers.59.mlp.up_proj.trellis": {
"shape": [
512,
352,
64
],
"n_bytes": 23068672,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.59.mlp.gate_proj": {
"stored_tensors": {
"model.layers.59.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.59.mlp.gate_proj.svh": {
"shape": [
5632
],
"n_bytes": 11264,
"dtype": "torch.float16"
},
"model.layers.59.mlp.gate_proj.trellis": {
"shape": [
512,
352,
64
],
"n_bytes": 23068672,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.59.mlp.down_proj": {
"stored_tensors": {
"model.layers.59.mlp.down_proj.suh": {
"shape": [
5632
],
"n_bytes": 11264,
"dtype": "torch.float16"
},
"model.layers.59.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.59.mlp.down_proj.trellis": {
"shape": [
352,
512,
64
],
"n_bytes": 23068672,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.60.post_attention_layernorm": {
"stored_tensors": {
"model.layers.60.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.60.mlp.up_proj": {
"stored_tensors": {
"model.layers.60.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.60.mlp.up_proj.svh": {
"shape": [
7168
],
"n_bytes": 14336,
"dtype": "torch.float16"
},
"model.layers.60.mlp.up_proj.trellis": {
"shape": [
512,
448,
64
],
"n_bytes": 29360128,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.60.mlp.gate_proj": {
"stored_tensors": {
"model.layers.60.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.60.mlp.gate_proj.svh": {
"shape": [
7168
],
"n_bytes": 14336,
"dtype": "torch.float16"
},
"model.layers.60.mlp.gate_proj.trellis": {
"shape": [
512,
448,
64
],
"n_bytes": 29360128,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.60.mlp.down_proj": {
"stored_tensors": {
"model.layers.60.mlp.down_proj.suh": {
"shape": [
7168
],
"n_bytes": 14336,
"dtype": "torch.float16"
},
"model.layers.60.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.60.mlp.down_proj.trellis": {
"shape": [
448,
512,
64
],
"n_bytes": 29360128,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.61.post_attention_layernorm": {
"stored_tensors": {
"model.layers.61.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.61.mlp.up_proj": {
"stored_tensors": {
"model.layers.61.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.61.mlp.up_proj.svh": {
"shape": [
7168
],
"n_bytes": 14336,
"dtype": "torch.float16"
},
"model.layers.61.mlp.up_proj.trellis": {
"shape": [
512,
448,
64
],
"n_bytes": 29360128,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.61.mlp.gate_proj": {
"stored_tensors": {
"model.layers.61.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.61.mlp.gate_proj.svh": {
"shape": [
7168
],
"n_bytes": 14336,
"dtype": "torch.float16"
},
"model.layers.61.mlp.gate_proj.trellis": {
"shape": [
512,
448,
64
],
"n_bytes": 29360128,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.61.mlp.down_proj": {
"stored_tensors": {
"model.layers.61.mlp.down_proj.suh": {
"shape": [
7168
],
"n_bytes": 14336,
"dtype": "torch.float16"
},
"model.layers.61.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.61.mlp.down_proj.trellis": {
"shape": [
448,
512,
64
],
"n_bytes": 29360128,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.62.post_attention_layernorm": {
"stored_tensors": {
"model.layers.62.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.62.mlp.up_proj": {
"stored_tensors": {
"model.layers.62.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.62.mlp.up_proj.svh": {
"shape": [
2816
],
"n_bytes": 5632,
"dtype": "torch.float16"
},
"model.layers.62.mlp.up_proj.trellis": {
"shape": [
512,
176,
64
],
"n_bytes": 11534336,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.62.mlp.gate_proj": {
"stored_tensors": {
"model.layers.62.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.62.mlp.gate_proj.svh": {
"shape": [
2816
],
"n_bytes": 5632,
"dtype": "torch.float16"
},
"model.layers.62.mlp.gate_proj.trellis": {
"shape": [
512,
176,
64
],
"n_bytes": 11534336,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.62.mlp.down_proj": {
"stored_tensors": {
"model.layers.62.mlp.down_proj.suh": {
"shape": [
2816
],
"n_bytes": 5632,
"dtype": "torch.float16"
},
"model.layers.62.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.62.mlp.down_proj.trellis": {
"shape": [
176,
512,
64
],
"n_bytes": 11534336,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.63.post_attention_layernorm": {
"stored_tensors": {
"model.layers.63.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.63.mlp.up_proj": {
"stored_tensors": {
"model.layers.63.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.63.mlp.up_proj.svh": {
"shape": [
2816
],
"n_bytes": 5632,
"dtype": "torch.float16"
},
"model.layers.63.mlp.up_proj.trellis": {
"shape": [
512,
176,
64
],
"n_bytes": 11534336,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.63.mlp.gate_proj": {
"stored_tensors": {
"model.layers.63.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.63.mlp.gate_proj.svh": {
"shape": [
2816
],
"n_bytes": 5632,
"dtype": "torch.float16"
},
"model.layers.63.mlp.gate_proj.trellis": {
"shape": [
512,
176,
64
],
"n_bytes": 11534336,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.63.mlp.down_proj": {
"stored_tensors": {
"model.layers.63.mlp.down_proj.suh": {
"shape": [
2816
],
"n_bytes": 5632,
"dtype": "torch.float16"
},
"model.layers.63.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.63.mlp.down_proj.trellis": {
"shape": [
176,
512,
64
],
"n_bytes": 11534336,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.64.post_attention_layernorm": {
"stored_tensors": {
"model.layers.64.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.64.mlp.up_proj": {
"stored_tensors": {
"model.layers.64.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.64.mlp.up_proj.svh": {
"shape": [
5632
],
"n_bytes": 11264,
"dtype": "torch.float16"
},
"model.layers.64.mlp.up_proj.trellis": {
"shape": [
512,
352,
64
],
"n_bytes": 23068672,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.64.mlp.gate_proj": {
"stored_tensors": {
"model.layers.64.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.64.mlp.gate_proj.svh": {
"shape": [
5632
],
"n_bytes": 11264,
"dtype": "torch.float16"
},
"model.layers.64.mlp.gate_proj.trellis": {
"shape": [
512,
352,
64
],
"n_bytes": 23068672,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.64.mlp.down_proj": {
"stored_tensors": {
"model.layers.64.mlp.down_proj.suh": {
"shape": [
5632
],
"n_bytes": 11264,
"dtype": "torch.float16"
},
"model.layers.64.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.64.mlp.down_proj.trellis": {
"shape": [
352,
512,
64
],
"n_bytes": 23068672,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.65.post_attention_layernorm": {
"stored_tensors": {
"model.layers.65.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.65.mlp.up_proj": {
"stored_tensors": {
"model.layers.65.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.65.mlp.up_proj.svh": {
"shape": [
5632
],
"n_bytes": 11264,
"dtype": "torch.float16"
},
"model.layers.65.mlp.up_proj.trellis": {
"shape": [
512,
352,
64
],
"n_bytes": 23068672,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.65.mlp.gate_proj": {
"stored_tensors": {
"model.layers.65.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.65.mlp.gate_proj.svh": {
"shape": [
5632
],
"n_bytes": 11264,
"dtype": "torch.float16"
},
"model.layers.65.mlp.gate_proj.trellis": {
"shape": [
512,
352,
64
],
"n_bytes": 23068672,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.65.mlp.down_proj": {
"stored_tensors": {
"model.layers.65.mlp.down_proj.suh": {
"shape": [
5632
],
"n_bytes": 11264,
"dtype": "torch.float16"
},
"model.layers.65.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.65.mlp.down_proj.trellis": {
"shape": [
352,
512,
64
],
"n_bytes": 23068672,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.66.post_attention_layernorm": {
"stored_tensors": {
"model.layers.66.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.66.mlp.up_proj": {
"stored_tensors": {
"model.layers.66.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.66.mlp.up_proj.svh": {
"shape": [
2816
],
"n_bytes": 5632,
"dtype": "torch.float16"
},
"model.layers.66.mlp.up_proj.trellis": {
"shape": [
512,
176,
64
],
"n_bytes": 11534336,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.66.mlp.gate_proj": {
"stored_tensors": {
"model.layers.66.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.66.mlp.gate_proj.svh": {
"shape": [
2816
],
"n_bytes": 5632,
"dtype": "torch.float16"
},
"model.layers.66.mlp.gate_proj.trellis": {
"shape": [
512,
176,
64
],
"n_bytes": 11534336,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.66.mlp.down_proj": {
"stored_tensors": {
"model.layers.66.mlp.down_proj.suh": {
"shape": [
2816
],
"n_bytes": 5632,
"dtype": "torch.float16"
},
"model.layers.66.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.66.mlp.down_proj.trellis": {
"shape": [
176,
512,
64
],
"n_bytes": 11534336,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.67.post_attention_layernorm": {
"stored_tensors": {
"model.layers.67.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.67.mlp.up_proj": {
"stored_tensors": {
"model.layers.67.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.67.mlp.up_proj.svh": {
"shape": [
2816
],
"n_bytes": 5632,
"dtype": "torch.float16"
},
"model.layers.67.mlp.up_proj.trellis": {
"shape": [
512,
176,
64
],
"n_bytes": 11534336,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.67.mlp.gate_proj": {
"stored_tensors": {
"model.layers.67.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.67.mlp.gate_proj.svh": {
"shape": [
2816
],
"n_bytes": 5632,
"dtype": "torch.float16"
},
"model.layers.67.mlp.gate_proj.trellis": {
"shape": [
512,
176,
64
],
"n_bytes": 11534336,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.67.mlp.down_proj": {
"stored_tensors": {
"model.layers.67.mlp.down_proj.suh": {
"shape": [
2816
],
"n_bytes": 5632,
"dtype": "torch.float16"
},
"model.layers.67.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.67.mlp.down_proj.trellis": {
"shape": [
176,
512,
64
],
"n_bytes": 11534336,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.68.post_attention_layernorm": {
"stored_tensors": {
"model.layers.68.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.68.mlp.up_proj": {
"stored_tensors": {
"model.layers.68.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.68.mlp.up_proj.svh": {
"shape": [
5632
],
"n_bytes": 11264,
"dtype": "torch.float16"
},
"model.layers.68.mlp.up_proj.trellis": {
"shape": [
512,
352,
64
],
"n_bytes": 23068672,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.68.mlp.gate_proj": {
"stored_tensors": {
"model.layers.68.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.68.mlp.gate_proj.svh": {
"shape": [
5632
],
"n_bytes": 11264,
"dtype": "torch.float16"
},
"model.layers.68.mlp.gate_proj.trellis": {
"shape": [
512,
352,
64
],
"n_bytes": 23068672,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.68.mlp.down_proj": {
"stored_tensors": {
"model.layers.68.mlp.down_proj.suh": {
"shape": [
5632
],
"n_bytes": 11264,
"dtype": "torch.float16"
},
"model.layers.68.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.68.mlp.down_proj.trellis": {
"shape": [
352,
512,
64
],
"n_bytes": 23068672,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.69.post_attention_layernorm": {
"stored_tensors": {
"model.layers.69.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.69.mlp.up_proj": {
"stored_tensors": {
"model.layers.69.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.69.mlp.up_proj.svh": {
"shape": [
2816
],
"n_bytes": 5632,
"dtype": "torch.float16"
},
"model.layers.69.mlp.up_proj.trellis": {
"shape": [
512,
176,
64
],
"n_bytes": 11534336,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.69.mlp.gate_proj": {
"stored_tensors": {
"model.layers.69.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.69.mlp.gate_proj.svh": {
"shape": [
2816
],
"n_bytes": 5632,
"dtype": "torch.float16"
},
"model.layers.69.mlp.gate_proj.trellis": {
"shape": [
512,
176,
64
],
"n_bytes": 11534336,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.69.mlp.down_proj": {
"stored_tensors": {
"model.layers.69.mlp.down_proj.suh": {
"shape": [
2816
],
"n_bytes": 5632,
"dtype": "torch.float16"
},
"model.layers.69.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.69.mlp.down_proj.trellis": {
"shape": [
176,
512,
64
],
"n_bytes": 11534336,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.70.post_attention_layernorm": {
"stored_tensors": {
"model.layers.70.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.70.mlp.up_proj": {
"stored_tensors": {
"model.layers.70.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.70.mlp.up_proj.svh": {
"shape": [
2816
],
"n_bytes": 5632,
"dtype": "torch.float16"
},
"model.layers.70.mlp.up_proj.trellis": {
"shape": [
512,
176,
64
],
"n_bytes": 11534336,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.70.mlp.gate_proj": {
"stored_tensors": {
"model.layers.70.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.70.mlp.gate_proj.svh": {
"shape": [
2816
],
"n_bytes": 5632,
"dtype": "torch.float16"
},
"model.layers.70.mlp.gate_proj.trellis": {
"shape": [
512,
176,
64
],
"n_bytes": 11534336,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.70.mlp.down_proj": {
"stored_tensors": {
"model.layers.70.mlp.down_proj.suh": {
"shape": [
2816
],
"n_bytes": 5632,
"dtype": "torch.float16"
},
"model.layers.70.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.70.mlp.down_proj.trellis": {
"shape": [
176,
512,
64
],
"n_bytes": 11534336,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.71.input_layernorm": {
"stored_tensors": {
"model.layers.71.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.71.self_attn.q_proj": {
"stored_tensors": {
"model.layers.71.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.71.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.71.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.71.self_attn.k_proj": {
"stored_tensors": {
"model.layers.71.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.71.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.71.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.71.self_attn.v_proj": {
"stored_tensors": {
"model.layers.71.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.71.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.71.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.71.self_attn.o_proj": {
"stored_tensors": {
"model.layers.71.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.71.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.71.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.71.post_attention_layernorm": {
"stored_tensors": {
"model.layers.71.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.71.mlp.up_proj": {
"stored_tensors": {
"model.layers.71.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.71.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.71.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.71.mlp.gate_proj": {
"stored_tensors": {
"model.layers.71.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.71.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.71.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.71.mlp.down_proj": {
"stored_tensors": {
"model.layers.71.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.71.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.71.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.72.input_layernorm": {
"stored_tensors": {
"model.layers.72.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.72.self_attn.q_proj": {
"stored_tensors": {
"model.layers.72.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.72.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.72.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.72.self_attn.k_proj": {
"stored_tensors": {
"model.layers.72.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.72.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.72.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.72.self_attn.v_proj": {
"stored_tensors": {
"model.layers.72.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.72.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.72.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.72.self_attn.o_proj": {
"stored_tensors": {
"model.layers.72.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.72.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.72.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.72.post_attention_layernorm": {
"stored_tensors": {
"model.layers.72.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.72.mlp.up_proj": {
"stored_tensors": {
"model.layers.72.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.72.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.72.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.72.mlp.gate_proj": {
"stored_tensors": {
"model.layers.72.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.72.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.72.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.72.mlp.down_proj": {
"stored_tensors": {
"model.layers.72.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.72.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.72.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.73.input_layernorm": {
"stored_tensors": {
"model.layers.73.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.73.self_attn.q_proj": {
"stored_tensors": {
"model.layers.73.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.73.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.73.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.73.self_attn.k_proj": {
"stored_tensors": {
"model.layers.73.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.73.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.73.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.73.self_attn.v_proj": {
"stored_tensors": {
"model.layers.73.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.73.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.73.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.73.self_attn.o_proj": {
"stored_tensors": {
"model.layers.73.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.73.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.73.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.73.post_attention_layernorm": {
"stored_tensors": {
"model.layers.73.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.73.mlp.up_proj": {
"stored_tensors": {
"model.layers.73.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.73.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.73.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.73.mlp.gate_proj": {
"stored_tensors": {
"model.layers.73.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.73.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.73.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.73.mlp.down_proj": {
"stored_tensors": {
"model.layers.73.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.73.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.73.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.74.input_layernorm": {
"stored_tensors": {
"model.layers.74.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.74.self_attn.q_proj": {
"stored_tensors": {
"model.layers.74.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.74.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.74.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.74.self_attn.k_proj": {
"stored_tensors": {
"model.layers.74.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.74.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.74.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.74.self_attn.v_proj": {
"stored_tensors": {
"model.layers.74.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.74.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.74.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.74.self_attn.o_proj": {
"stored_tensors": {
"model.layers.74.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.74.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.74.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.74.post_attention_layernorm": {
"stored_tensors": {
"model.layers.74.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.74.mlp.up_proj": {
"stored_tensors": {
"model.layers.74.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.74.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.74.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.74.mlp.gate_proj": {
"stored_tensors": {
"model.layers.74.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.74.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.74.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.74.mlp.down_proj": {
"stored_tensors": {
"model.layers.74.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.74.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.74.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.75.input_layernorm": {
"stored_tensors": {
"model.layers.75.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.75.self_attn.q_proj": {
"stored_tensors": {
"model.layers.75.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.75.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.75.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.75.self_attn.k_proj": {
"stored_tensors": {
"model.layers.75.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.75.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.75.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.75.self_attn.v_proj": {
"stored_tensors": {
"model.layers.75.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.75.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.75.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.75.self_attn.o_proj": {
"stored_tensors": {
"model.layers.75.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.75.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.75.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.75.post_attention_layernorm": {
"stored_tensors": {
"model.layers.75.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.75.mlp.up_proj": {
"stored_tensors": {
"model.layers.75.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.75.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.75.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.75.mlp.gate_proj": {
"stored_tensors": {
"model.layers.75.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.75.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.75.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.75.mlp.down_proj": {
"stored_tensors": {
"model.layers.75.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.75.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.75.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.76.input_layernorm": {
"stored_tensors": {
"model.layers.76.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.76.self_attn.q_proj": {
"stored_tensors": {
"model.layers.76.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.76.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.76.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.76.self_attn.k_proj": {
"stored_tensors": {
"model.layers.76.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.76.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.76.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.76.self_attn.v_proj": {
"stored_tensors": {
"model.layers.76.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.76.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.76.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.76.self_attn.o_proj": {
"stored_tensors": {
"model.layers.76.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.76.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.76.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.76.post_attention_layernorm": {
"stored_tensors": {
"model.layers.76.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.76.mlp.up_proj": {
"stored_tensors": {
"model.layers.76.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.76.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.76.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.76.mlp.gate_proj": {
"stored_tensors": {
"model.layers.76.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.76.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.76.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.76.mlp.down_proj": {
"stored_tensors": {
"model.layers.76.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.76.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.76.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.77.input_layernorm": {
"stored_tensors": {
"model.layers.77.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.77.self_attn.q_proj": {
"stored_tensors": {
"model.layers.77.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.77.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.77.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.77.self_attn.k_proj": {
"stored_tensors": {
"model.layers.77.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.77.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.77.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.77.self_attn.v_proj": {
"stored_tensors": {
"model.layers.77.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.77.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.77.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.77.self_attn.o_proj": {
"stored_tensors": {
"model.layers.77.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.77.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.77.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.77.post_attention_layernorm": {
"stored_tensors": {
"model.layers.77.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.77.mlp.up_proj": {
"stored_tensors": {
"model.layers.77.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.77.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.77.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.77.mlp.gate_proj": {
"stored_tensors": {
"model.layers.77.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.77.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.77.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.77.mlp.down_proj": {
"stored_tensors": {
"model.layers.77.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.77.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.77.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.78.input_layernorm": {
"stored_tensors": {
"model.layers.78.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.78.self_attn.q_proj": {
"stored_tensors": {
"model.layers.78.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.78.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.78.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.78.self_attn.k_proj": {
"stored_tensors": {
"model.layers.78.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.78.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.78.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.78.self_attn.v_proj": {
"stored_tensors": {
"model.layers.78.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.78.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.78.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.78.self_attn.o_proj": {
"stored_tensors": {
"model.layers.78.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.78.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.78.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.78.post_attention_layernorm": {
"stored_tensors": {
"model.layers.78.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.78.mlp.up_proj": {
"stored_tensors": {
"model.layers.78.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.78.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.78.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.78.mlp.gate_proj": {
"stored_tensors": {
"model.layers.78.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.78.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.78.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.78.mlp.down_proj": {
"stored_tensors": {
"model.layers.78.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.78.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.78.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.79.input_layernorm": {
"stored_tensors": {
"model.layers.79.input_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.79.self_attn.q_proj": {
"stored_tensors": {
"model.layers.79.self_attn.q_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.79.self_attn.q_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.79.self_attn.q_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.79.self_attn.k_proj": {
"stored_tensors": {
"model.layers.79.self_attn.k_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.79.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.79.self_attn.k_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.79.self_attn.v_proj": {
"stored_tensors": {
"model.layers.79.self_attn.v_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.79.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.79.self_attn.v_proj.trellis": {
"shape": [
512,
64,
64
],
"n_bytes": 4194304,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.79.self_attn.o_proj": {
"stored_tensors": {
"model.layers.79.self_attn.o_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.79.self_attn.o_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.79.self_attn.o_proj.trellis": {
"shape": [
512,
512,
64
],
"n_bytes": 33554432,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.79.post_attention_layernorm": {
"stored_tensors": {
"model.layers.79.post_attention_layernorm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"model.layers.79.mlp.up_proj": {
"stored_tensors": {
"model.layers.79.mlp.up_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.79.mlp.up_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.79.mlp.up_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.79.mlp.gate_proj": {
"stored_tensors": {
"model.layers.79.mlp.gate_proj.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.79.mlp.gate_proj.svh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.79.mlp.gate_proj.trellis": {
"shape": [
512,
1792,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.79.mlp.down_proj": {
"stored_tensors": {
"model.layers.79.mlp.down_proj.suh": {
"shape": [
28672
],
"n_bytes": 57344,
"dtype": "torch.float16"
},
"model.layers.79.mlp.down_proj.svh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"model.layers.79.mlp.down_proj.trellis": {
"shape": [
1792,
512,
64
],
"n_bytes": 117440512,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.norm": {
"stored_tensors": {
"model.norm.weight": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
}
}
},
"lm_head": {
"stored_tensors": {
"lm_head.suh": {
"shape": [
8192
],
"n_bytes": 16384,
"dtype": "torch.float16"
},
"lm_head.svh": {
"shape": [
128256
],
"n_bytes": 256512,
"dtype": "torch.float16"
},
"lm_head.trellis": {
"shape": [
512,
8016,
128
],
"n_bytes": 1050673152,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 8
}
}
}