Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Lora: fix rank 1 loras #575

Merged
merged 2 commits into from
Feb 5, 2025
Merged

Lora: fix rank 1 loras #575

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
dea49bf
Lora: fix rank 1 loras
stduhpf Jan 20, 2025
86678a1
lora: format
stduhpf Jan 22, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 6 additions & 3 deletions lora.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -615,9 +615,12 @@ struct LoraModel : public GGMLRunner {
scale_value *= multiplier;

// flat lora tensors to multiply it
int64_t lora_up_rows = lora_up->ne[ggml_n_dims(lora_up) - 1];
lora_up = ggml_reshape_2d(compute_ctx, lora_up, ggml_nelements(lora_up) / lora_up_rows, lora_up_rows);
int64_t lora_down_rows = lora_down->ne[ggml_n_dims(lora_down) - 1];
int64_t lora_up_rows = lora_up->ne[ggml_n_dims(lora_up) - 1];
lora_up = ggml_reshape_2d(compute_ctx, lora_up, ggml_nelements(lora_up) / lora_up_rows, lora_up_rows);
auto lora_down_n_dims = ggml_n_dims(lora_down);
// assume n_dims should always be a multiple of 2 (otherwise rank 1 doesn't work)
lora_down_n_dims = (lora_down_n_dims + lora_down_n_dims % 2);
int64_t lora_down_rows = lora_down->ne[lora_down_n_dims - 1];
lora_down = ggml_reshape_2d(compute_ctx, lora_down, ggml_nelements(lora_down) / lora_down_rows, lora_down_rows);

// ggml_mul_mat requires tensor b transposed
Expand Down
Loading