convert-*.py: GGUF Naming Convention Refactor and Metadata Override Refactor (#7499)

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>
This commit is contained in:
Brian 2024-07-18 20:40:15 +10:00 committed by GitHub
parent 3807c3de04
commit 672a6f1018
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
13 changed files with 1185 additions and 239 deletions

View file

@ -19,19 +19,60 @@ GGML_QUANT_VERSION = 2 # GGML_QNT_VERSION from ggml.h
class Keys:
class General:
TYPE = "general.type"
ARCHITECTURE = "general.architecture"
QUANTIZATION_VERSION = "general.quantization_version"
ALIGNMENT = "general.alignment"
NAME = "general.name"
AUTHOR = "general.author"
VERSION = "general.version"
URL = "general.url"
DESCRIPTION = "general.description"
LICENSE = "general.license"
SOURCE_URL = "general.source.url"
SOURCE_HF_REPO = "general.source.huggingface.repository"
FILE_TYPE = "general.file_type"
TYPE = "general.type"
ARCHITECTURE = "general.architecture"
QUANTIZATION_VERSION = "general.quantization_version"
ALIGNMENT = "general.alignment"
FILE_TYPE = "general.file_type"
# Authorship Metadata
NAME = "general.name"
AUTHOR = "general.author"
VERSION = "general.version"
ORGANIZATION = "general.organization"
FINETUNE = "general.finetune"
BASENAME = "general.basename"
DESCRIPTION = "general.description"
QUANTIZED_BY = "general.quantized_by"
SIZE_LABEL = "general.size_label"
# Licensing details
LICENSE = "general.license"
LICENSE_NAME = "general.license.name"
LICENSE_LINK = "general.license.link"
# Typically represents the converted GGUF repo (Unless native)
URL = "general.url" # Model Website/Paper
DOI = "general.doi"
UUID = "general.uuid"
REPO_URL = "general.repo_url" # Model Source Repository (git/svn/etc...)
# Model Source during conversion
SOURCE_URL = "general.source.url" # Model Website/Paper
SOURCE_DOI = "general.source.doi"
SOURCE_UUID = "general.source.uuid"
SOURCE_REPO_URL = "general.source.repo_url" # Model Source Repository (git/svn/etc...)
# Base Model Source. There can be more than one source if it's a merged
# model like with 'Mistral-7B-Merge-14-v0.1'. This will assist in
# tracing linage of models as it is finetuned or merged over time.
BASE_MODEL_COUNT = "general.base_model.count"
BASE_MODEL_NAME = "general.base_model.{id}.name"
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_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...)
# Array based KV stores
TAGS = "general.tags"
LANGUAGES = "general.languages"
DATASETS = "general.datasets"
class LLM:
VOCAB_SIZE = "{arch}.vocab_size"
@ -1233,7 +1274,6 @@ KEY_GENERAL_URL = Keys.General.URL
KEY_GENERAL_DESCRIPTION = Keys.General.DESCRIPTION
KEY_GENERAL_LICENSE = Keys.General.LICENSE
KEY_GENERAL_SOURCE_URL = Keys.General.SOURCE_URL
KEY_GENERAL_SOURCE_HF_REPO = Keys.General.SOURCE_HF_REPO
KEY_GENERAL_FILE_TYPE = Keys.General.FILE_TYPE
# LLM