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

* convert : fix python 3.8 support

* convert : sort imports

* convert : fix required parameters in convert-llama-ggmlv3-to-gguf

* convert : fix mypy errors in convert-llama-ggmlv3-to-gguf

* convert : use PEP 585 generics and PEP 604 unions

Now that we have `from __future__ import annotations`, we can use this
modern syntax in Python 3.7 instead of restricting support to Python 3.9
or 3.10 respectively.

* gguf.py : a tuple is already a tuple

* add mypy.ini

* convert : add necessary `type: ignore` comments

* gguf-py: bump version
This commit is contained in:
Cebtenzzre 2023-08-31 01:02:23 -04:00 committed by GitHub
parent 8afe228000
commit 92d0b751a7
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
10 changed files with 193 additions and 168 deletions

View file

@ -1,18 +1,20 @@
#!/usr/bin/env python3
# HF gptneox--> gguf conversion
import gguf
import os
import sys
import struct
from __future__ import annotations
import argparse
import json
import os
import struct
import sys
from pathlib import Path
from typing import Any
import gguf
import numpy as np
import torch
import argparse
from typing import Any, List
from pathlib import Path
from transformers import AutoTokenizer
from transformers import AutoTokenizer # type: ignore[import]
# ref: https://github.com/openai/gpt-2/blob/master/src/encoder.py
@ -112,7 +114,7 @@ gguf_writer.add_layer_norm_eps(hparams["layer_norm_eps"])
print("gguf: get tokenizer metadata")
tokens: List[bytearray] = []
tokens: list[bytearray] = []
tokenizer_json_file = dir_model / 'tokenizer.json'
if not tokenizer_json_file.is_file():