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.

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

Possible solution to allow K-quants on models with n_vocab!=32000 #2148

Merged
merged 3 commits into from
Jul 11, 2023
Merged
Changes from 1 commit
Commits
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
Next Next commit
Fix indentation
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
LostRuins and ggerganov authored Jul 10, 2023
commit 048dca9809dbfb8acf37a21cf130235c465532bd
3 changes: 1 addition & 2 deletions llama.cpp
Original file line number Diff line number Diff line change
@@ -2464,8 +2464,7 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s
if (ftype == LLAMA_FTYPE_MOSTLY_Q3_K_M || ftype == LLAMA_FTYPE_MOSTLY_Q2_K) new_type = GGML_TYPE_Q4_K;
else if (ftype == LLAMA_FTYPE_MOSTLY_Q3_K_L) new_type = GGML_TYPE_Q5_K;
}
if(convert_incompatible_tensor)
{
if (convert_incompatible_tensor) {
new_type = GGML_TYPE_Q8_0; //fall back to Q8_0 instead of just failing.
}
#endif