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

Jump to bottom

Add Q3_K_XS #5060

Merged
merged 2 commits into from
Jan 22, 2024
Merged

Add Q3_K_XS #5060

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ec4b801
Add Q3_K_XS - intermediate size between Q2_K and Q3_K_S
Kawrakow Jan 21, 2024
29c41d4
Q3_K_XS: quanize first 1/8 of ffn_down layers with Q4_K
Kawrakow Jan 21, 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
Prev Previous commit
Q3_K_XS: quanize first 1/8 of ffn_down layers with Q4_K 
Together with an importance matrix, this brings perplexity
for LLaMA-v2-70B below the perplexity of the former Q2_K
with a 800 MB smaller quantized model size.
  • Loading branch information
@Kawrakow
Kawrakow committed Jan 21, 2024
commit 29c41d49fe024d3791cd7b683c6c85fcf80a370e
2 changes: 1 addition & 1 deletion llama.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8934,7 +8934,7 @@ static ggml_type get_k_quant_type(quantize_state_internal & qs, ggml_type new_ty
}
}
if (ftype == LLAMA_FTYPE_MOSTLY_Q2_K) new_type = GGML_TYPE_Q3_K;
else if (ftype == LLAMA_FTYPE_MOSTLY_Q2_K_S) {
else if (ftype == LLAMA_FTYPE_MOSTLY_Q2_K_S || ftype == LLAMA_FTYPE_MOSTLY_Q3_K_XS) {
if (i_layer < n_layer/8) new_type = GGML_TYPE_Q4_K;
}
else if (ftype == LLAMA_FTYPE_MOSTLY_Q3_K_M) {
Expand Down
Loading