Update config.json
Browse files- config.json +2 -2
config.json
CHANGED
@@ -39,7 +39,7 @@
|
|
39 |
"model_name_or_path": null,
|
40 |
"model_file_base_name": "model",
|
41 |
"quant_method": "gptq",
|
42 |
-
"
|
43 |
["self_attn.k_proj", "self_attn.v_proj", "self_attn.q_proj"],
|
44 |
["self_attn.o_proj"],
|
45 |
["block_sparse_moe.experts.0.w1", "block_sparse_moe.experts.0.w2", "block_sparse_moe.experts.0.w3"],
|
@@ -49,6 +49,6 @@
|
|
49 |
["block_sparse_moe.experts.4.w1", "block_sparse_moe.experts.4.w2", "block_sparse_moe.experts.4.w3"],
|
50 |
["block_sparse_moe.experts.5.w1", "block_sparse_moe.experts.5.w2", "block_sparse_moe.experts.5.w3"],
|
51 |
["block_sparse_moe.experts.6.w1", "block_sparse_moe.experts.6.w2", "block_sparse_moe.experts.6.w3"],
|
52 |
-
["block_sparse_moe.experts.7.w1", "block_sparse_moe.experts.7.w2", "block_sparse_moe.experts.7.w3"]]
|
53 |
}
|
54 |
}
|
|
|
39 |
"model_name_or_path": null,
|
40 |
"model_file_base_name": "model",
|
41 |
"quant_method": "gptq",
|
42 |
+
"modules_in_block_to_quantize" : [
|
43 |
["self_attn.k_proj", "self_attn.v_proj", "self_attn.q_proj"],
|
44 |
["self_attn.o_proj"],
|
45 |
["block_sparse_moe.experts.0.w1", "block_sparse_moe.experts.0.w2", "block_sparse_moe.experts.0.w3"],
|
|
|
49 |
["block_sparse_moe.experts.4.w1", "block_sparse_moe.experts.4.w2", "block_sparse_moe.experts.4.w3"],
|
50 |
["block_sparse_moe.experts.5.w1", "block_sparse_moe.experts.5.w2", "block_sparse_moe.experts.5.w3"],
|
51 |
["block_sparse_moe.experts.6.w1", "block_sparse_moe.experts.6.w2", "block_sparse_moe.experts.6.w3"],
|
52 |
+
["block_sparse_moe.experts.7.w1", "block_sparse_moe.experts.7.w2", "block_sparse_moe.experts.7.w3"]],
|
53 |
}
|
54 |
}
|