mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-10-30 06:30:15 +01:00
672a6f1018
Main thing is that the default output filename will take this form
{name}{parameters}{finetune}{version}{encoding}{kind}
In addition this add and remove some entries in the KV store and adds a metadata class with automatic heuristics capability to derive some values based on model card content
* No Change:
- Internal GGUF Spec
- `general.architecture`
- `general.quantization_version`
- `general.alignment`
- `general.file_type`
- General Model Details
- `general.name`
- `general.author`
- `general.version`
- `general.description`
- Licensing details
- `general.license`
- Typically represents the converted GGUF repo (Unless made from scratch)
- `general.url`
- Model Source during conversion
- `general.source.url`
* Removed:
- Model Source during conversion
- `general.source.huggingface.repository`
* Added:
- General Model Details
- `general.organization`
- `general.finetune`
- `general.basename`
- `general.quantized_by`
- `general.size_label`
- Licensing details
- `general.license.name`
- `general.license.link`
- Typically represents the converted GGUF repo (Unless made from scratch)
- `general.doi`
- `general.uuid`
- `general.repo_url`
- Model Source during conversion
- `general.source.doi`
- `general.source.uuid`
- `general.source.repo_url`
- Base Model Source
- `general.base_model.count`
- `general.base_model.{id}.name`
- `general.base_model.{id}.author`
- `general.base_model.{id}.version`
- `general.base_model.{id}.organization`
- `general.base_model.{id}.url` (Model Website/Paper)
- `general.base_model.{id}.doi`
- `general.base_model.{id}.uuid`
- `general.base_model.{id}.repo_url` (Model Source Repository (git/svn/etc...))
- Array based KV stores
- `general.tags`
- `general.languages`
- `general.datasets`
---------
Co-authored-by: compilade <git@compilade.net>
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
39 lines
1013 B
TOML
39 lines
1013 B
TOML
[tool.poetry]
|
|
name = "gguf"
|
|
version = "0.9.1"
|
|
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"
|
|
tqdm = ">=4.27"
|
|
pyyaml = ">=5.1"
|
|
|
|
[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"
|