8000 convert : fix handling of added tokens by cebtenzzre · Pull Request #3405 · ggml-org/llama.cpp · GitHub
[go: up one dir, main page]
Skip to content

convert : fix handling of added tokens #3405

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

Closed
wants to merge 5 commits into from
Closed

convert : fix handling of added tokens #3405

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
846c51f
convert : use bytes_to_unicode from transformers
cebtenzzre Sep 29, 2023
8c8b5b0
convert : fix handling of added tokens
cebtenzzre Sep 29, 2023
f18cfea
s/else if/elif/
cebtenzzre Oct 1, 2023
02fbbf9
fix typo
cebtenzzre Oct 1, 2023
1115a09
Merge upstream into fix-convert-added-tokens
cebtenzzre Oct 4, 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
s/else if/elif/
  • Loading branch information
@cebtenzzre
cebtenzzre committed Oct 1, 2023
commit f18cfeab62ca426be5d73cdf8547d8cd48bd9cde
2 changes: 1 addition & 1 deletion convert-falcon-hf-to-gguf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -144,7 +144,7 @@ def parse_args() -> argparse.Namespace:
print(f"Key {i} not in tokenizer vocabulary. Padding with an arbitrary token.")
pad_token = f"[PAD{i}]".encode("utf8")
text = bytearray(pad_token)
else if i in added_tokens:
elif i in added_tokens:
# these tokens are not encoded, see https://github.com/huggingface/transformers/issues/1133
text = bytearray(reverse_vocab[i].encode('utf-8'))
else:
Expand Down
2 changes: 1 addition & 1 deletion convert-gptneox-hf-to-gguf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -140,7 +140,7 @@ def parse_args() -> argparse.Namespace:
print(f"Key {i} not in tokenizer vocabulary. Padding with an arbitrary token.")
pad_token = f"[PAD{i}]".encode("utf8")
text = bytearray(pad_token)
else if i in added_tokens:
elif i in added_tokens:
# these tokens are not encoded, see https://github.com/huggingface/transformers/issues/1133
text = bytearray(reverse_vocab[i].encode('utf-8'))
else:
Expand Down
2 changes: 1 addition & 1 deletion convert-starcoder-hf-to-gguf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -128,7 +128,7 @@ def parse_args() -> argparse.Namespace:
print(f"Key {i} not in tokenizer vocabulary. Padding with an arbitrary token.")
pad_token = f"[PAD{i}]".encode("utf8")
text = bytearray(pad_token)
else if i in added_tokens:
elif i in added_tokens:
# these tokens are not encoded, see https://github.com/huggingface/transformers/issues/1133
text = bytearray(reverse_vocab[i].encode('utf-8'))
else:
Expand Down
0