|
{ |
|
"measurement": { |
|
"model.layers.0": { |
|
"accuracy": 0.877131462097168, |
|
"total_bits": 606753024, |
|
"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": { |
|
"4": 128 |
|
}, |
|
"bits": [ |
|
4 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
} |
|
}, |
|
"model.layers.1": { |
|
"accuracy": 0.8948612213134766, |
|
"total_bits": 573724416, |
|
"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": { |
|
"4": 128 |
|
}, |
|
"bits": [ |
|
4 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
} |
|
}, |
|
"model.layers.2": { |
|
"accuracy": 0.9520481824874878, |
|
"total_bits": 458124288, |
|
"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": 0.9584293961524963, |
|
"total_bits": 466380288, |
|
"q_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"k_proj": { |
|
"group_size": { |
|
"4": 128 |
|
}, |
|
"bits": [ |
|
4 |
|
], |
|
"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": 0.9498380422592163, |
|
"total_bits": 458124288, |
|
"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": 0.9403245449066162, |
|
"total_bits": 458124288, |
|
"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": 0.9329239130020142, |
|
"total_bits": 458124288, |
|
"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": 0.9157736301422119, |
|
"total_bits": 458124288, |
|
"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": 0.9307241439819336, |
|
"total_bits": 491152896, |
|
"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.9": { |
|
"accuracy": 0.9189841747283936, |
|
"total_bits": 458124288, |
|
"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": 0.9128692150115967, |
|
"total_bits": 458124288, |
|
"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": 0.9105658531188965, |
|
"total_bits": 458124288, |
|
"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": 0.9119572639465332, |
|
"total_bits": 491152896, |
|
"q_proj": { |
|
"group_size": { |
|
"4": 128 |
|
}, |
|
"bits": [ |
|
4 |
|
], |
|
"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": 0.9047572612762451, |
|
"total_bits": 458124288, |
|
"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": 0.8954880237579346, |
|
"total_bits": 458124288, |
|
"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": 0.8818550109863281, |
|
"total_bits": 458124288, |
|
"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": 0.8823418617248535, |
|
"total_bits": 458124288, |
|
"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": 0.8916378021240234, |
|
"total_bits": 491152896, |
|
"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.18": { |
|
"accuracy": 0.8813910484313965, |
|
"total_bits": 491152896, |
|
"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.19": { |
|
"accuracy": 0.879364013671875, |
|
"total_bits": 491152896, |
|
"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.20": { |
|
"accuracy": 0.8831210136413574, |
|
"total_bits": 458124288, |
|
"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": 0.8880167007446289, |
|
"total_bits": 458124288, |
|
"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": 0.8944659233093262, |
|
"total_bits": 458124288, |
|
"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": 0.8957762718200684, |
|
"total_bits": 466380288, |
|
"q_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"k_proj": { |
|
"group_size": { |
|
"4": 128 |
|
}, |
|
"bits": [ |
|
4 |
|
], |
|
"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.24": { |
|
"accuracy": 0.892493724822998, |
|
"total_bits": 458124288, |
|
"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.25": { |
|
"accuracy": 0.8929567337036133, |
|
"total_bits": 458124288, |
|
"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.26": { |
|
"accuracy": 0.8940300941467285, |
|
"total_bits": 466380288, |
|
"q_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"k_proj": { |
|
"group_size": { |
|
"4": 128 |
|
}, |
|
"bits": [ |
|
4 |
|
], |
|
"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.27": { |
|
"accuracy": 0.8957915306091309, |
|
"total_bits": 466380288, |
|
"q_proj": { |
|
"group_size": { |
|
"2": 64 |
|
}, |
|
"bits": [ |
|
2 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
}, |
|
"k_proj": { |
|
"group_size": { |
|
"4": 128 |
|
}, |
|
"bits": [ |
|
4 |
|
], |
|
"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.28": { |
|
"accuracy": 0.8838896751403809, |
|
"total_bits": 458124288, |
|
"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.29": { |
|
"accuracy": 0.8807954788208008, |
|
"total_bits": 458124288, |
|
"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.30": { |
|
"accuracy": 0.9012184143066406, |
|
"total_bits": 573724416, |
|
"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": { |
|
"4": 128 |
|
}, |
|
"bits": [ |
|
4 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
} |
|
}, |
|
"model.layers.31": { |
|
"accuracy": 0.8941550254821777, |
|
"total_bits": 573724416, |
|
"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": { |
|
"4": 128 |
|
}, |
|
"bits": [ |
|
4 |
|
], |
|
"bits_prop": [ |
|
1 |
|
], |
|
"scale_bits": 4 |
|
} |
|
} |
|
} |
|
} |