|
{ |
|
"('model.layers.0.self_attn.q_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.0.self_attn.k_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.0.self_attn.v_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.0.self_attn.o_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.0.mlp.gate_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.0.mlp.up_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.0.mlp.down_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.1.self_attn.q_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.1.self_attn.k_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.1.self_attn.v_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.1.self_attn.o_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.1.mlp.gate_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.1.mlp.up_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.1.mlp.down_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.2.self_attn.q_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.2.self_attn.k_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.2.self_attn.v_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.2.self_attn.o_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.2.mlp.gate_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.2.mlp.up_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.2.mlp.down_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.3.self_attn.q_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.3.self_attn.k_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.3.self_attn.v_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.3.self_attn.o_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.3.mlp.gate_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.3.mlp.up_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.3.mlp.down_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.4.self_attn.q_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.4.self_attn.k_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.4.self_attn.v_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.4.self_attn.o_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.4.mlp.gate_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.4.mlp.up_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.4.mlp.down_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.5.self_attn.q_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.5.self_attn.k_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.5.self_attn.v_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.5.self_attn.o_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.5.mlp.gate_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.5.mlp.up_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.5.mlp.down_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.6.self_attn.q_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.6.self_attn.k_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.6.self_attn.v_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.6.self_attn.o_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.6.mlp.gate_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.6.mlp.up_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.6.mlp.down_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.7.self_attn.q_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.7.self_attn.k_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.7.self_attn.v_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.7.self_attn.o_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.7.mlp.gate_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.7.mlp.up_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.7.mlp.down_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.8.self_attn.q_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.8.self_attn.k_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.8.self_attn.v_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.8.self_attn.o_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.8.mlp.gate_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.8.mlp.up_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.8.mlp.down_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.9.self_attn.q_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.9.self_attn.k_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.9.self_attn.v_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.9.self_attn.o_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.9.mlp.gate_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.9.mlp.up_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.9.mlp.down_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.10.self_attn.q_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.10.self_attn.k_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.10.self_attn.v_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.10.self_attn.o_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.10.mlp.gate_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.10.mlp.up_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.10.mlp.down_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.11.self_attn.q_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.11.self_attn.k_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.11.self_attn.v_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.11.self_attn.o_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.11.mlp.gate_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.11.mlp.up_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.11.mlp.down_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.12.self_attn.q_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.12.self_attn.k_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.12.self_attn.v_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.12.self_attn.o_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.12.mlp.gate_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.12.mlp.up_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.12.mlp.down_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.13.self_attn.q_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.13.self_attn.k_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.13.self_attn.v_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.13.self_attn.o_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.13.mlp.gate_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.13.mlp.up_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.13.mlp.down_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.14.self_attn.q_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.14.self_attn.k_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.14.self_attn.v_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.14.self_attn.o_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.14.mlp.gate_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.14.mlp.up_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.14.mlp.down_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.15.self_attn.q_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.15.self_attn.k_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.15.self_attn.v_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.15.self_attn.o_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.15.mlp.gate_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.15.mlp.up_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('model.layers.15.mlp.down_proj.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
}, |
|
"('lm_head.orig_layer', 'Linear')": { |
|
"teq": { |
|
"dtype": "int", |
|
"bits": 4, |
|
"use_sym": false, |
|
"group_size": 128, |
|
"group_dim": 1, |
|
"use_full_range": false, |
|
"use_mse_search": false, |
|
"use_layer_wise": false, |
|
"use_double_quant": false, |
|
"double_quant_bits": 8, |
|
"double_quant_dtype": "int", |
|
"double_quant_use_sym": true, |
|
"double_quant_group_size": 256, |
|
"quant_lm_head": true, |
|
"absorb_to_layer": {}, |
|
"folding": false |
|
} |
|
} |
|
} |