Skip to content

fixed potential memory leak, deleted unnecessary semicolon #34

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

Open
mendax0110 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fixed potential memory leak, deleted unnecessary semicolon #34

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
fixed potential memory leak in the load_model function , deleted se… 
…micolons
  • Loading branch information
@mendax0110
mendax0110 committed Sep 9, 2023
commit fb27a45f54831ec21440da51355c0eedc9d89d5c
3 changes: 3 additions & 0 deletions StarCoderApp/starcoderlib/generate.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -714,6 +714,9 @@ extern const StarcoderModel * load_model(const char * model_path) {

if (!starcoder_model_load(model_path, model->model, model->vocab)) {
fprintf(stderr, "%s: failed to load model from '%s'\n", __func__, model_path);

// free the mem, allocated for 'model' before returning
delete model;
return NULL;
}

Expand Down
6 changes: 3 additions & 3 deletions convert-hf-to-ggml.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -160,10 +160,10 @@ def bytes_to_unicode():
print(" Skipping variable: " + name)
continue

n_dims = len(data.shape);
n_dims = len(data.shape)

# ftype == 0 -> float32, ftype == 1 -> float16
ftype = 0;
ftype = 0
if use_f16:
if (name == "model/wte" or name == "model/lm_head" or name[-2:] == "/g" or name[-2:] == "/w") and n_dims == 2:
print(" Converting to float16")
Expand Down Expand Up @@ -201,7 +201,7 @@ def bytes_to_unicode():
fout.write(struct.pack("iii", n_dims, len(str), ftype))
for i in range(n_dims):
fout.write(struct.pack("i", data.shape[n_dims - 1 - i]))
fout.write(str);
fout.write(str)

# data
data.tofile(fout)
Expand Down