|
{ |
|
"measurement": { |
|
"model.layers.0": { |
|
"accuracy": 0.6466712951660156, |
|
"total_bits": 28563648, |
|
"q_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"k_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"v_proj": { |
|
"group_size": { |
|
"4": 128 |
|
}, |
|
"bits": [ |
|
4 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"o_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"up_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"gate_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"down_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
} |
|
}, |
|
"model.layers.1": { |
|
"accuracy": 0.8311243057250977, |
|
"total_bits": 28563648, |
|
"q_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"k_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"v_proj": { |
|
"group_size": { |
|
"4": 128 |
|
}, |
|
"bits": [ |
|
4 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"o_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"up_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"gate_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"down_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
} |
|
}, |
|
"model.layers.2": { |
|
"accuracy": 0.8292713165283203, |
|
"total_bits": 28563648, |
|
"q_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"k_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"v_proj": { |
|
"group_size": { |
|
"4": 128 |
|
}, |
|
"bits": [ |
|
4 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"o_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"up_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"gate_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"down_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
} |
|
}, |
|
"model.layers.3": { |
|
"accuracy": 0.8550562858581543, |
|
"total_bits": 28563648, |
|
"q_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"k_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"v_proj": { |
|
"group_size": { |
|
"4": 128 |
|
}, |
|
"bits": [ |
|
4 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"o_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"up_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"gate_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"down_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
} |
|
}, |
|
"model.layers.4": { |
|
"accuracy": 0.8643341064453125, |
|
"total_bits": 28563648, |
|
"q_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"k_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"v_proj": { |
|
"group_size": { |
|
"4": 128 |
|
}, |
|
"bits": [ |
|
4 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"o_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"up_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"gate_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"down_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
} |
|
}, |
|
"model.layers.5": { |
|
"accuracy": 0.7996025085449219, |
|
"total_bits": 28563648, |
|
"q_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"k_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"v_proj": { |
|
"group_size": { |
|
"4": 128 |
|
}, |
|
"bits": [ |
|
4 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"o_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"up_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"gate_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"down_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
} |
|
}, |
|
"model.layers.6": { |
|
"accuracy": 0.8700046539306641, |
|
"total_bits": 28563648, |
|
"q_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"k_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"v_proj": { |
|
"group_size": { |
|
"4": 128 |
|
}, |
|
"bits": [ |
|
4 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"o_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"up_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"gate_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"down_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
} |
|
}, |
|
"model.layers.7": { |
|
"accuracy": 0.8551735877990723, |
|
"total_bits": 28563648, |
|
"q_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"k_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"v_proj": { |
|
"group_size": { |
|
"4": 128 |
|
}, |
|
"bits": [ |
|
4 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"o_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"up_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"gate_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"down_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
} |
|
}, |
|
"model.layers.8": { |
|
"accuracy": 0.8605437278747559, |
|
"total_bits": 28563648, |
|
"q_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"k_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"v_proj": { |
|
"group_size": { |
|
"4": 128 |
|
}, |
|
"bits": [ |
|
4 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"o_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"up_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"gate_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"down_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
} |
|
}, |
|
"model.layers.9": { |
|
"accuracy": 0.8751955032348633, |
|
"total_bits": 28563648, |
|
"q_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"k_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"v_proj": { |
|
"group_size": { |
|
"4": 128 |
|
}, |
|
"bits": [ |
|
4 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"o_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"up_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"gate_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"down_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
} |
|
}, |
|
"model.layers.10": { |
|
"accuracy": 0.8496556282043457, |
|
"total_bits": 28563648, |
|
"q_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"k_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"v_proj": { |
|
"group_size": { |
|
"4": 128 |
|
}, |
|
"bits": [ |
|
4 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"o_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"up_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"gate_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"down_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
} |
|
}, |
|
"model.layers.11": { |
|
"accuracy": 0.8491725921630859, |
|
"total_bits": 28563648, |
|
"q_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"k_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"v_proj": { |
|
"group_size": { |
|
"4": 128 |
|
}, |
|
"bits": [ |
|
4 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"o_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"up_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"gate_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"down_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
} |
|
}, |
|
"model.layers.12": { |
|
"accuracy": 0.8609495162963867, |
|
"total_bits": 28563648, |
|
"q_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"k_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"v_proj": { |
|
"group_size": { |
|
"4": 128 |
|
}, |
|
"bits": [ |
|
4 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"o_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"up_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"gate_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"down_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
} |
|
}, |
|
"model.layers.13": { |
|
"accuracy": 0.8702535629272461, |
|
"total_bits": 28563648, |
|
"q_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"k_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"v_proj": { |
|
"group_size": { |
|
"4": 128 |
|
}, |
|
"bits": [ |
|
4 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"o_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"up_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"gate_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"down_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
} |
|
}, |
|
"model.layers.14": { |
|
"accuracy": 0.864326000213623, |
|
"total_bits": 28563648, |
|
"q_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"k_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"v_proj": { |
|
"group_size": { |
|
"4": 128 |
|
}, |
|
"bits": [ |
|
4 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"o_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"up_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"gate_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"down_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
} |
|
}, |
|
"model.layers.15": { |
|
"accuracy": 0.8553919792175293, |
|
"total_bits": 28563648, |
|
"q_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"k_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"v_proj": { |
|
"group_size": { |
|
"4": 128 |
|
}, |
|
"bits": [ |
|
4 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"o_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"up_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"gate_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"down_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
} |
|
}, |
|
"model.layers.16": { |
|
"accuracy": 0.8639998435974121, |
|
"total_bits": 28563648, |
|
"q_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"k_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"v_proj": { |
|
"group_size": { |
|
"4": 128 |
|
}, |
|
"bits": [ |
|
4 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"o_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"up_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"gate_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"down_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
} |
|
}, |
|
"model.layers.17": { |
|
"accuracy": 0.8462457656860352, |
|
"total_bits": 28563648, |
|
"q_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"k_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"v_proj": { |
|
"group_size": { |
|
"4": 128 |
|
}, |
|
"bits": [ |
|
4 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"o_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"up_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"gate_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"down_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
} |
|
}, |
|
"model.layers.18": { |
|
"accuracy": 0.8548283576965332, |
|
"total_bits": 28563648, |
|
"q_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"k_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"v_proj": { |
|
"group_size": { |
|
"4": 128 |
|
}, |
|
"bits": [ |
|
4 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"o_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"up_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"gate_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"down_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
} |
|
}, |
|
"model.layers.19": { |
|
"accuracy": 0.8628249168395996, |
|
"total_bits": 28563648, |
|
"q_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"k_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"v_proj": { |
|
"group_size": { |
|
"4": 128 |
|
}, |
|
"bits": [ |
|
4 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"o_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"up_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"gate_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"down_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
} |
|
}, |
|
"model.layers.20": { |
|
"accuracy": 0.8636555671691895, |
|
"total_bits": 28563648, |
|
"q_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"k_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"v_proj": { |
|
"group_size": { |
|
"4": 128 |
|
}, |
|
"bits": [ |
|
4 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"o_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"up_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"gate_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"down_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
} |
|
}, |
|
"model.layers.21": { |
|
"accuracy": 0.873690128326416, |
|
"total_bits": 28563648, |
|
"q_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"k_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"v_proj": { |
|
"group_size": { |
|
"4": 128 |
|
}, |
|
"bits": [ |
|
4 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"o_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"up_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"gate_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"down_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
} |
|
}, |
|
"model.layers.22": { |
|
"accuracy": 0.8687443733215332, |
|
"total_bits": 28563648, |
|
"q_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"k_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"v_proj": { |
|
"group_size": { |
|
"4": 128 |
|
}, |
|
"bits": [ |
|
4 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"o_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"up_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"gate_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"down_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
} |
|
}, |
|
"model.layers.23": { |
|
"accuracy": 0.8376064300537109, |
|
"total_bits": 28563648, |
|
"q_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"k_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"v_proj": { |
|
"group_size": { |
|
"4": 128 |
|
}, |
|
"bits": [ |
|
4 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"o_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"up_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"gate_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"down_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
} |
|
} |
|
} |
|
} |