Skip to content

Adding Gemma 2 2B configs #8784

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

Merged
merged 2 commits into from
Jul 31, 2024
Merged

Adding Gemma 2 2B configs #8784

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
9b4294d
Adding Gemma 2 2B configs
pculliton Jul 31, 2024
36e6685
Update src/llama.cpp
pculliton Jul 31, 2024
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
2 changes: 2 additions & 0 deletions src/llama.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4969,6 +4969,7 @@ static void llm_load_hparams(
hparams.attn_soft_cap = true;

switch (hparams.n_layer) {
case 26: model.type = e_model::MODEL_2B; break;
case 42: model.type = e_model::MODEL_9B; break;
case 46: model.type = e_model::MODEL_27B; break;
default: model.type = e_model::MODEL_UNKNOWN;
Expand Down Expand Up @@ -11736,6 +11737,7 @@ struct llm_build_context {

// ref: https://github.com/google/gemma_pytorch/commit/03e657582d17cb5a8617ebf333c1c16f3694670e
switch (model.type) {
case e_model::MODEL_2B:
case e_model::MODEL_9B: Qcur = ggml_scale(ctx0, Qcur, 1.0f / sqrtf(float(n_embd_head_k))); break;
case e_model::MODEL_27B: Qcur = ggml_scale(ctx0, Qcur, 1.0f / sqrtf(float(n_embd / n_head))); break;
default: GGML_ABORT("fatal error");
Expand Down
Loading