|
{ |
|
"measurement": { |
|
"model.layers.0": { |
|
"accuracy": 0.7405672073364258, |
|
"total_bits": 120876576, |
|
"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": { |
|
"4": 128 |
|
}, |
|
"bits": [ |
|
4 |
|
], |
|
"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": 0.8317708969116211, |
|
"total_bits": 112619808, |
|
"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": 0.8587737083435059, |
|
"total_bits": 112619808, |
|
"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": 0.8670854568481445, |
|
"total_bits": 112619808, |
|
"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": 0.8640389442443848, |
|
"total_bits": 112619808, |
|
"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": 0.8391742706298828, |
|
"total_bits": 112619808, |
|
"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": 0.7521486282348633, |
|
"total_bits": 120876576, |
|
"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": { |
|
"4": 128 |
|
}, |
|
"bits": [ |
|
4 |
|
], |
|
"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": 0.9208848476409912, |
|
"total_bits": 112619808, |
|
"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": 0.9133262634277344, |
|
"total_bits": 112619808, |
|
"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": 0.9102234840393066, |
|
"total_bits": 112619808, |
|
"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": 0.9021768569946289, |
|
"total_bits": 112619808, |
|
"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": 0.9006736278533936, |
|
"total_bits": 112619808, |
|
"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": 0.8896198272705078, |
|
"total_bits": 112619808, |
|
"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": 0.8880295753479004, |
|
"total_bits": 112619808, |
|
"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": 0.8788719177246094, |
|
"total_bits": 112619808, |
|
"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": 0.8800616264343262, |
|
"total_bits": 112619808, |
|
"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": 0.8750381469726562, |
|
"total_bits": 112619808, |
|
"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": 0.8723258972167969, |
|
"total_bits": 112619808, |
|
"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": 0.8696107864379883, |
|
"total_bits": 112619808, |
|
"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": 0.8691720962524414, |
|
"total_bits": 112619808, |
|
"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": 0.8783330917358398, |
|
"total_bits": 112619808, |
|
"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": 0.8743820190429688, |
|
"total_bits": 112619808, |
|
"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": 0.8673934936523438, |
|
"total_bits": 112619808, |
|
"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": 0.8243818283081055, |
|
"total_bits": 112619808, |
|
"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 |
|
} |
|
} |
|
} |
|
} |