vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

convert-*.py: add general.organization to kv store

Browse source
This commit is contained in:
brian khuu 2024-06-03 00:57:37 +10:00
parent f7c20793b9
commit 5a86dfaa1c
5 changed files with 21 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

2
convert_hf_to_gguf.py
View file

@ -244,6 +244,8 @@ class Model:
self.gguf_writer.add_finetune(self.metadata.finetune)
if self.metadata.author is not None:
self.gguf_writer.add_author(self.metadata.author)
if self.metadata.organization is not None:
self.gguf_writer.add_organization(self.metadata.organization)
if self.metadata.version is not None:
self.gguf_writer.add_version(self.metadata.version)
if self.metadata.base_version is not None:

6
examples/convert_legacy_llama.py
View file

@ -789,6 +789,8 @@ class OutputFile:
self.gguf.add_finetune(metadata.finetune)
if metadata.author is not None:
self.gguf.add_author(metadata.author)
if metadata.organization is not None:
self.add_organization(metadata.organization)
if metadata.version is not None:
self.gguf.add_version(metadata.version)
if metadata.base_version is not None:
@ -805,6 +807,10 @@ class OutputFile:
self.gguf.add_source_hf_repo(metadata.source_hf_repo)
if metadata.tags is not None:
self.gguf_writer.add_tags(metadata.tags)
if metadata.languages is not None:
self.gguf_writer.add_languages(metadata.languages)
if metadata.datasets is not None:
self.gguf_writer.add_datasets(metadata.datasets)
def add_meta_arch(self, params: Params) -> None:
# Metadata About The Neural Architecture Itself

3
gguf-py/gguf/constants.py
View file

@ -27,6 +27,7 @@ class Keys:
BASENAME = "general.basename"
FINETUNE = "general.finetune"
AUTHOR = "general.author"
ORGANIZATION = "general.organization"
VERSION = "general.version"
BASE_VERSION = "general.base_version"
URL = "general.url"
@ -39,7 +40,7 @@ class Keys:
FILE_TYPE = "general.file_type"
PARAMETER_SIZE_CLASS = "general.parameter_size_class"
TAGS = "general.tags"
LANGUAGE = "general.language"
LANGUAGES = "general.languages"
DATASETS = "general.datasets"
class LLM:

5
gguf-py/gguf/gguf_writer.py
View file

@ -439,6 +439,9 @@ class GGUFWriter:
def add_author(self, author: str) -> None:
self.add_string(Keys.General.AUTHOR, author)
def add_organization(self, organization: str) -> None:
self.add_string(Keys.General.ORGANIZATION, organization)
def add_version(self, version: str) -> None:
self.add_string(Keys.General.VERSION, version)
@ -479,7 +482,7 @@ class GGUFWriter:
self.add_array(Keys.Tokenizer.TAGS, tags)
def add_languages(self, languages: Sequence[str]) -> None:
self.add_array(Keys.Tokenizer.LANGUAGE, languages)
self.add_array(Keys.Tokenizer.LANGUAGES, languages)
def add_datasets(self, datasets: Sequence[str]) -> None:
self.add_array(Keys.Tokenizer.DATASETS, datasets)

12
gguf-py/gguf/metadata.py
View file

@ -15,6 +15,7 @@ class Metadata:
basename: Optional[str] = None
finetune: Optional[str] = None
author: Optional[str] = None
organization: Optional[str] = None
version: Optional[str] = None
base_version: Optional[str] = None
url: Optional[str] = None
@ -26,7 +27,7 @@ class Metadata:
source_hf_repo: Optional[str] = None
parameter_size_class: Optional[str] = None
tags: Optional[list[str]] = None
language: Optional[list[str]] = None
languages: Optional[list[str]] = None
datasets: Optional[list[str]] = None
@staticmethod
@ -38,7 +39,7 @@ class Metadata:
# Create a new Metadata instance
metadata = Metadata()
# load model folder model card if available
# load huggingface model card if available
# Reference Model Card Metadata: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1
model_card = Metadata.load_model_card(model_path)
if metadata.name is None:
@ -61,9 +62,9 @@ class Metadata:
if metadata.tags is None:
metadata.tags = model_card.get("tags", [])
if metadata.languages is None:
metadata.languages = model_card.get("languages", [])
metadata.languages = model_card.get("language", model_card.get("languages", []))
if metadata.datasets is None:
metadata.datasets = model_card.get("datasets", [])
metadata.datasets = model_card.get("datasets", model_card.get("dataset", []))
# load huggingface parameters if available
hf_params = Metadata.load_huggingface_parameters(model_path)
@ -85,6 +86,7 @@ class Metadata:
metadata.basename = metadata_override.get(Keys.General.BASENAME , metadata.basename ) # noqa: E202
metadata.finetune = metadata_override.get(Keys.General.FINETUNE , metadata.finetune ) # noqa: E202
metadata.author = metadata_override.get(Keys.General.AUTHOR , metadata.author ) # noqa: E202
metadata.organization = metadata_override.get(Keys.General.ORGANIZATION , metadata.organization ) # noqa: E202
metadata.version = metadata_override.get(Keys.General.VERSION , metadata.version ) # noqa: E202
metadata.base_version = metadata_override.get(Keys.General.BASE_VERSION , metadata.base_version ) # noqa: E202
metadata.url = metadata_override.get(Keys.General.URL , metadata.url ) # noqa: E202
@ -97,7 +99,7 @@ class Metadata:
metadata.parameter_size_class = metadata_override.get(Keys.General.PARAMETER_SIZE_CLASS, metadata.parameter_size_class) # noqa: E202
metadata.tags = metadata_override.get(Keys.General.TAGS , metadata.tags ) # noqa: E202
metadata.languages = metadata_override.get(Keys.General.LANGUAGES , metadata.languages ) # noqa: E202
metadata.datasets = metadata_override.get(Keys.General.datasets , metadata.datasets ) # noqa: E202
metadata.datasets = metadata_override.get(Keys.General.DATASETS , metadata.datasets ) # noqa: E202
# Direct Metadata Override (via direct cli argument)
if model_name is not None: