8000 gemma : use more bits for the token_embd.weight tensor by ggerganov · Pull Request #5650 · ggml-org/llama.cpp · GitHub
[go: up one dir, main page]
Skip to content

gemma : use more bits for the token_embd.weight tensor #5650

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
Feb 22, 2024
Merged

gemma : use more bits for the token_embd.weight tensor #5650

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f181e60
gemma : use Q8_0 for the token_embd.weight tensor
ggerganov Feb 21, 2024
488bd97
llama : quantize token_embd.weight using output type
ggerganov Feb 22, 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
Next Next commit
gemma : use Q8_0 for the token_embd.weight tensor
  • Loading branch information
@ggerganov
ggerganov committed Feb 21, 2024
commit f181e601a166be5f8b77414e17194c4c9a924d68
3 changes: 3 additions & 0 deletions llama.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10499,6 +10499,9 @@ static ggml_type get_k_quant_type(quantize_state_internal & qs, ggml_type new_ty
else if (ftype == LLAMA_FTYPE_MOSTLY_IQ3_XXS) {
new_type = GGML_TYPE_Q4_K;
}
else if (arch == LLM_ARCH_GEMMA) {
new_type = GGML_TYPE_Q8_0;
}
} else if (ftype == LLAMA_FTYPE_MOSTLY_IQ2_XXS || ftype == LLAMA_FTYPE_MOSTLY_IQ2_XS || ftype == LLAMA_FTYPE_MOSTLY_IQ1_S) {
if (name.find("attn_v.weight") != std::string::npos) {
if (qs.model.hparams.n_gqa() >= 4 || qs.model.hparams.n_expert >= 4) new_type = GGML_TYPE_Q4_K;
Expand Down
0