10000 convert : fix python 3.8 support, modernize type annotations by cebtenzzre · Pull Request #2916 · ggml-org/llama.cpp · GitHub
[go: up one dir, main page]
Skip to content

convert : fix python 3.8 support, modernize type annotations #2916

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
Aug 31, 2023
Merged

convert : fix python 3.8 support, modernize type annotations #2916

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
b18159b
convert : fix python 3.8 support
cebtenzzre Aug 30, 2023
a09b674
convert : sort imports
cebtenzzre Aug 30, 2023
68738ff
convert : fix required parameters in convert-llama-ggmlv3-to-gguf
cebtenzzre Aug 30, 2023
f30937a
convert : fix mypy errors in convert-llama-ggmlv3-to-gguf
cebtenzzre Aug 30, 2023
ef87d46
convert : use PEP 585 generics and PEP 604 unions
cebtenzzre Aug 30, 2023
42a0768
gguf.py : a tuple is already a tuple
cebtenzzre Aug 30, 2023
e66e0be
add mypy.ini
cebtenzzre Aug 30, 2023
8a8c1cb
convert : add necessary `type: ignore` comments
cebtenzzre Aug 30, 2023
05df178
gguf-py: bump version
cebtenzzre Aug 30, 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
convert : add necessary type: ignore comments
  • Loading branch information
@cebtenzzre
cebtenzzre committed Aug 30, 2023
commit 8a8c1cb0f2881bb5172c13c55e22ea80c72bef5a
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 @@ -14,7 +14,7 @@
import gguf
import numpy as np
import torch
from transformers import AutoTokenizer
from transformers import AutoTokenizer # type: ignore[import]


def bytes_to_unicode():
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 @@ -14,7 +14,7 @@
import gguf
import numpy as np
import torch
from transformers import AutoTokenizer
from transformers import AutoTokenizer # type: ignore[import]

# ref: https://github.com/openai/gpt-2/blob/master/src/encoder.py

Expand Down
2 changes: 1 addition & 1 deletion convert-llama-7b-pth-to-gguf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@
import gguf
import numpy as np
import torch
from sentencepiece import SentencePieceProcessor
from sentencepiece import SentencePieceProcessor # type: ignore[import]

if TYPE_CHECKING:
from typing import TypeAlias
Expand Down
2 changes: 1 addition & 1 deletion convert-llama-hf-to-gguf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,7 @@
import gguf
import numpy as np
import torch
from sentencepiece import SentencePieceProcessor
from sentencepiece import SentencePieceProcessor # type: ignore[import]

if TYPE_CHECKING:
from typing import TypeAlias
Expand Down
4 changes: 2 additions & 2 deletions convert.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@

import gguf
import numpy as np
from sentencepiece import SentencePieceProcessor # type: ignore
from sentencepiece import SentencePieceProcessor # type: ignore[import]

if TYPE_CHECKING:
from typing import TypeAlias
Expand Down Expand Up @@ -338,7 +338,7 @@ def __init__(self, fname_tokenizer: Path, fname_added_tokens: Path | None) -> No

def bpe_tokens(self) -> Iterable[tuple[bytes, float, gguf.TokenType]]:
tokenizer = self.bpe_tokenizer
from transformers.models.gpt2 import tokenization_gpt2
from transformers.models.gpt2 import tokenization_gpt2 # type: ignore[import]
byte_encoder = tokenization_gpt2.bytes_to_unicode()
byte_decoder = {v: k for k, v in byte_encoder.items()}
for i, item in enumerate(tokenizer):
Expand Down
0