CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-08 10:07:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

metadata: Detailed Dataset Authorship Metadata (#8875)

Browse Source 
Converter script can now read these two fields as a detailed base model and dataset source.
This was done so that it will be easier for Hugging Face to integrate detailed metadata as needed.

 -  base_model_sources (List[dict], optional)
 -  dataset_sources (List[dict], optional)

Dataset now represented as:

 - general.dataset.count
 - general.dataset.{id}.name
 - general.dataset.{id}.author
 - general.dataset.{id}.version
 - general.dataset.{id}.organization
 - general.dataset.{id}.description
 - general.dataset.{id}.url
 - general.dataset.{id}.doi
 - general.dataset.{id}.uuid
 - general.dataset.{id}.repo_url

This also adds to base model these metadata:

 - general.base_model.{id}.description
This commit is contained in:
Brian
2024-11-13 21:10:38 +11:00
committed by GitHub
parent 2e82ffa4af
commit a0ec17b32e
5 changed files with 233 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
gguf-py/gguf/constants.py
View File

@@ -64,15 +64,27 @@ class Keys:
BASE_MODEL_AUTHOR = "general.base_model.{id}.author"
BASE_MODEL_VERSION = "general.base_model.{id}.version"
BASE_MODEL_ORGANIZATION = "general.base_model.{id}.organization"
BASE_MODEL_DESCRIPTION = "general.base_model.{id}.description"
BASE_MODEL_URL = "general.base_model.{id}.url" # Model Website/Paper
BASE_MODEL_DOI = "general.base_model.{id}.doi"
BASE_MODEL_UUID = "general.base_model.{id}.uuid"
BASE_MODEL_REPO_URL = "general.base_model.{id}.repo_url" # Model Source Repository (git/svn/etc...)
# Dataset Source
DATASET_COUNT = "general.dataset.count"
DATASET_NAME = "general.dataset.{id}.name"
DATASET_AUTHOR = "general.dataset.{id}.author"
DATASET_VERSION = "general.dataset.{id}.version"
DATASET_ORGANIZATION = "general.dataset.{id}.organization"
DATASET_DESCRIPTION = "general.dataset.{id}.description"
DATASET_URL = "general.dataset.{id}.url" # Model Website/Paper
DATASET_DOI = "general.dataset.{id}.doi"
DATASET_UUID = "general.dataset.{id}.uuid"
DATASET_REPO_URL = "general.dataset.{id}.repo_url" # Model Source Repository (git/svn/etc...)
# Array based KV stores
TAGS = "general.tags"
LANGUAGES = "general.languages"
DATASETS = "general.datasets"
class LLM:
VOCAB_SIZE = "{arch}.vocab_size"