llama.cpp/gguf-py/pyproject.toml
Sigbjørn Skjæret 03c0946d73
convert : support models with multiple chat templates (#6588)
* Support converting models with multiple chat templates

Adds the following metadata:
* tokenizer.chat_templates
* tokenizer.chat_template.<name1>
* tokenizer.chat_template.<name2>
* tokenizer.chat_template.<...>

Where `tokenizer.chat_templates` is an array of the template names (except `default`), `default` is added to the regular `tokenizer.chat_template`.

* replace filtered characters with underscore

* New script to add/modify/remove metadata

This scripts creates a copy of a GGUF file and allows you to add/modify/remove metadata in the process.

Most importantly this allows you to update chat templates, either as a string or directly from an updated tokenizer_config.json file.

* Add files via upload

add new script to project/readme

* flake--
2024-04-18 14:49:01 +03:00

37 lines
980 B
TOML

[tool.poetry]
name = "gguf"
version = "0.9.0"
description = "Read and write ML models in GGUF for GGML"
authors = ["GGML <ggml@ggml.ai>"]
packages = [
{include = "gguf"},
{include = "gguf/py.typed"},
{include = "scripts"},
]
readme = "README.md"
homepage = "https://ggml.ai"
repository = "https://github.com/ggerganov/llama.cpp"
keywords = ["ggml", "gguf", "llama.cpp"]
classifiers = [
"Programming Language :: Python :: 3",
"License :: OSI Approved :: MIT License",
"Operating System :: OS Independent",
]
[tool.poetry.dependencies]
python = ">=3.8"
numpy = ">=1.17"
[tool.poetry.dev-dependencies]
pytest = "^5.2"
[build-system]
requires = ["poetry-core>=1.0.0"]
build-backend = "poetry.core.masonry.api"
[tool.poetry.scripts]
gguf-convert-endian = "scripts:gguf_convert_endian_entrypoint"
gguf-dump = "scripts:gguf_dump_entrypoint"
gguf-set-metadata = "scripts:gguf_set_metadata_entrypoint"
gguf-new-metadata = "scripts:gguf_new_metadata_entrypoint"