8000 Feature: support baichuan serial models, by now, including Baichuan-7… by jameswu2014 · Pull Request #3009 · ggml-org/llama.cpp · GitHub
[go: up one dir, main page]
Skip to content

Feature: support baichuan serial models, by now, including Baichuan-7… #3009

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 9 commits into from
Sep 14, 2023
Merged

Feature: support baichuan serial models, by now, including Baichuan-7… #3009

Changes from 1 commit
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
bd72ba0
Feature: support baichuan serial models, by now, including Baichuan-7…
jameswu2014 Sep 4, 2023
d1940a3
update format
jameswu2014 Sep 4, 2023
2cc8dce
Merge branch 'ggerganov:master' into master
jameswu2014 Sep 4, 2023
37873ae
update format
jameswu2014 Sep 4, 2023
9fd5aa7
fix baichuan1-13b W_pack convert bug
jameswu2014 Sep 5, 2023
c8863f3
feature: add prompts
jameswu2014 Sep 5, 2023
39c4b85
Merge branch 'ggerganov:master' into master
jameswu2014 Sep 5, 2023
306d71b
fix W_pack for-loop
jameswu2014 Sep 11, 2023
fa41aeb
update convert-baichuan limit of authority
jameswu2014 Sep 11, 2023
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 W_pack for-loop
  • Loading branch information
@jameswu2014
jameswu2014 committed Sep 11, 2023
commit 306d71be42f5cbac0208d17720b8161a90d7f836
2 changes: 1 addition & 1 deletion convert-baichuan-hf-to-gguf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -232,7 +232,7 @@ def parse_args() -> argparse.Namespace:
model_part = torch.load(f"{dir_model}/{part_name}", map_location="cpu")

tmp=model_part
for i in itertools.count():
for i in range(block_count):
if f"model.layers.{i}.self_attn.W_pack.weight" in model_part:
print(f"Unpacking and permuting layer {i}")
tmp[f"model.layers.{i}.self_attn.q_proj.weight"]=reverse_hf_permute_part(model_part[f"model.layers.{i}.self_attn.W_pack.weight"],0,head_count,head_count)
Expand Down
0