DarthAffe/stable-diffusion.cpp
1
0 Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-11-11 11:26:34 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: match exact weights in LLM config detection (#1923)

Browse Source
This commit is contained in:
leejet authored and GitHub committed 2026-08-30 17:43:41 +08:00
1 parent be0e34480d
commit 2c929495ab
1 file changed
+7 -7
Download Patch File Download Diff File Expand all files Collapse all files
src/model/te/llm.hpp
+7 -7
View File
@@ -232,12 +232,12 @@ namespace LLM {
} }
} }
} }
if (contains(name, "visual.blocks.0.mlp.linear_fc1.weight") || if (ends_with(name, "visual.blocks.0.mlp.linear_fc1.weight") ||
contains(name, "visual.blocks.0.mlp.gate_proj.weight")) { ends_with(name, "visual.blocks.0.mlp.gate_proj.weight")) {
config.vision.intermediate_size = tensor_storage.ne[1]; config.vision.intermediate_size = tensor_storage.ne[1];
} }
if (contains(name, "visual.merger.linear_fc2.weight") || if (ends_with(name, "visual.merger.linear_fc2.weight") ||
contains(name, "visual.merger.mlp.2.weight")) { ends_with(name, "visual.merger.mlp.2.weight")) {
config.vision.out_hidden_size = tensor_storage.ne[1]; config.vision.out_hidden_size = tensor_storage.ne[1];
} }
continue; continue;
@@ -256,13 +256,13 @@ namespace LLM {
config.hidden_size = tensor_storage.ne[0]; config.hidden_size = tensor_storage.ne[0];
config.vocab_size = tensor_storage.ne[1]; config.vocab_size = tensor_storage.ne[1];
} }
if (contains(name, "layers.0.mlp.gate_proj.weight")) { if (ends_with(name, "layers.0.mlp.gate_proj.weight")) {
config.intermediate_size = tensor_storage.ne[1]; config.intermediate_size = tensor_storage.ne[1];
} }
if (contains(name, "layers.0.mlp.experts.gate_up_proj.weight")) { if (ends_with(name, "layers.0.mlp.experts.gate_up_proj.weight")) {
config.intermediate_size = tensor_storage.ne[1] / 2; config.intermediate_size = tensor_storage.ne[1] / 2;
} }
if (contains(name, "layers.0.mlp.experts.gate_proj.weight")) { if (ends_with(name, "layers.0.mlp.experts.gate_proj.weight")) {
config.intermediate_size = tensor_storage.ne[1]; config.intermediate_size = tensor_storage.ne[1];
} }
} }