llama.cpp/gguf-py/pyproject.toml
Kerfuffle dc07dc492e
convert : various script cleanups/fixes + merges and special token handling (#2842)
* convert: Fix permute calls and method/func definitions

* Cleanups for gguf-py

* Minor types cleanups.

* Initial implementation of handling merges and special tokens

* convert: Handle special tokens and merges in vocab only mode

convert: Vocab only mode no longer requires loading model tensors

* gguf: Refactor tensor name mapping

* convert: Fix type hint for special_token_types in SpecialVocab

* Use common special vocab handling in various conversion scripts

* First pass at implementing suggested changes

* Second pass

* gguf: SpecialVocab: Fix issue with special token content not in a dict

gguf: SpecialVocab: Allow skipping handling of merges

* convert-falcon-hf-to-gguf: Support --vocab-only option, bail out if no tokenizer.json

* convert-gptneox-hf-to-gguf and convert: Only handle merges for BPE tokenizer

* gguf: SpecialVocab: Actually set load_merges in object

* Uniform args parsing and vocab only mode for convert examples

* convert.py: Set gpt2 as tokenizer model when using BPE

* Squish last type warning in gguf.py - yay!
2023-08-30 11:25:50 +03:00

30 lines
697 B
TOML

[tool.poetry]
name = "gguf"
version = "0.2.1"
description = "Write ML models in GGUF for GGML"
authors = ["GGML <ggml@ggml.ai>"]
packages = [
{include = "gguf"},
{include = "gguf/py.typed"},
]
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"