convert-*.py: GGUF Naming Convention Refactor and Metadata Override R…

…efactor (#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>

convert_lora_to_gguf.py

@@ -251,6 +251,10 @@ def parse_args() -> argparse.Namespace:
         "--verbose", action="store_true",
         help="increase output verbosity",
     )
+    parser.add_argument(
+        "--dry-run", action="store_true",
+        help="only print out what will be done, without writing any new files",
+    )
     parser.add_argument(
         "--base", type=Path, required=True,
         help="directory containing base model file",
@@ -300,6 +304,12 @@ def parse_args() -> argparse.Namespace:
     # load base model
     logger.info(f"Loading base model: {dir_base_model.name}")
     hparams = Model.load_hparams(dir_base_model)
+
+    with open(lora_config, "r") as f:
+        lparams: dict[str, Any] = json.load(f)
+
+    alpha: float = lparams["lora_alpha"]
+
     with torch.inference_mode():
         try:
             model_class = Model.from_model_architecture(hparams["architectures"][0])
@@ -310,6 +320,14 @@ def parse_args() -> argparse.Namespace:
         class LoraModel(model_class):
             model_arch = model_class.model_arch
 
+            def set_type(self):
+                self.gguf_writer.add_type(gguf.GGUFType.ADAPTER)
+                self.gguf_writer.add_string(gguf.Keys.Adapter.TYPE, "lora")
+
+            def set_gguf_parameters(self):
+                self.gguf_writer.add_float32(gguf.Keys.Adapter.LORA_ALPHA, float(alpha))
+                super().set_gguf_parameters()
+
             def get_tensors(self) -> Iterator[tuple[str, Tensor]]:
                 tensor_map: dict[str, PartialLoraTensor] = {}
 
@@ -357,18 +375,9 @@ def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iter
             is_big_endian=args.bigendian,
             use_temp_file=False,
             eager=args.no_lazy,
-            model_name=None,
+            dry_run=args.dry_run,
         )
 
-        with open(lora_config, "r") as f:
-            lparams: dict[str, Any] = json.load(f)
-
-        alpha = lparams["lora_alpha"]
-
-        model_instance.gguf_writer.add_string(gguf.Keys.General.TYPE, gguf.GGUFType.ADAPTER)
-        model_instance.gguf_writer.add_string(gguf.Keys.Adapter.TYPE, "lora")
-        model_instance.gguf_writer.add_float32(gguf.Keys.Adapter.LORA_ALPHA, float(alpha))
-        model_instance.gguf_writer.add_quantization_version(gguf.GGML_QUANT_VERSION)
         logger.info("Exporting model...")
         model_instance.write()
         logger.info(f"Model successfully exported to {model_instance.fname_out}")

gguf-py/README.md

@@ -78,5 +78,13 @@ python -m build
 python -m twine upload dist/*
 ```
 
+## Run Unit Tests
+
+From root of this repository you can run this command to run all the unit tests
+
+```bash
+python -m unittest discover ./gguf-py -v
+```
+
 ## TODO
 - [ ] Include conversion scripts as command line entry points in this package.

gguf-py/gguf/__init__.py

@@ -5,3 +5,5 @@
 from .quants import *
 from .tensor_mapping import *
 from .vocab import *
+from .utility import *
+from .metadata import *

gguf-py/gguf/constants.py

@@ -19,19 +19,60 @@
 
 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 @@ def get_type(val: Any) -> GGUFValueType:
 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

gguf-py/gguf/gguf_writer.py

@@ -7,6 +7,7 @@
 import tempfile
 from dataclasses import dataclass
 from enum import Enum, auto
+from math import prod
 from pathlib import Path
 from io import BufferedWriter
 from typing import IO, Any, Sequence, Mapping
@@ -106,6 +107,53 @@ def __init__(
 
         self.add_architecture()
 
+    def get_total_parameter_count(self) -> tuple[int, int, int, int]:
+        total_params = 0
+        shared_params = 0
+        expert_params = 0
+
+        expert_sum = 0
+        n_expert_tensors = 0
+
+        last_lora_a: tuple[str, TensorInfo] | None = None
+
+        for tensors in self.tensors:
+            for name, info in tensors.items():
+
+                shape = info.shape
+
+                if name.endswith(".lora_a"):
+                    last_lora_a = (name, info)
+                    continue
+                elif name.endswith(".lora_b"):
+                    if last_lora_a is None or last_lora_a[0] != name[:-1] + "a":
+                        # Bail when the LoRA pair can't be found trivially
+                        logger.warning("can't measure LoRA size correctly, tensor order is unusual")
+                        return 0, 0, 0, 0
+                    else:
+                        shape = (*shape[:-1], last_lora_a[1].shape[-1])
+
+                size = prod(shape)
+
+                if "_exps." in name:
+                    expert_params += (size // shape[-3])
+                    expert_sum += shape[-3]
+                    n_expert_tensors += 1
+                else:
+                    shared_params += size
+
+                total_params += size
+
+        # Hopefully this should work even for variable-expert-count models
+        expert_count = (expert_sum // n_expert_tensors) if n_expert_tensors > 0 else 0
+
+        # Negate the total to signal it's likely not exact
+        if last_lora_a is not None:
+            total_params = -total_params
+
+        # NOTE: keep the output in the same order as accepted by 'size_label' in gguf-py/gguf/utility.py
+        return total_params, shared_params, expert_params, expert_count
+
     def format_shard_names(self, path: Path) -> list[Path]:
         if len(self.tensors) == 1:
             return [path]
@@ -115,6 +163,7 @@ def open_output_file(self, path: Path | None = None) -> None:
         if self.state is WriterState.EMPTY and self.fout is not None and (path is None or path == self.path):
             # allow calling this multiple times as long as the path is the same
             return
+
         if self.state is not WriterState.NO_FILE:
             raise ValueError(f'Expected output file to be not yet opened, got {self.state}')
 
@@ -136,6 +185,8 @@ def print_plan(self) -> list[Path]:
 
         if self.dry_run:
             logger.info("Dry run, not writing files")
+            for name in filenames:
+                print(name)  # noqa: NP100
             exit()
 
         return filenames
@@ -430,43 +481,114 @@ def add_type(self, type_name: str) -> None:
     def add_architecture(self) -> None:
         self.add_string(Keys.General.ARCHITECTURE, self.arch)
 
+    def add_quantization_version(self, quantization_version: int) -> None:
+        self.add_uint32(Keys.General.QUANTIZATION_VERSION, quantization_version)
+
+    def add_custom_alignment(self, alignment: int) -> None:
+        self.data_alignment = alignment
+        self.add_uint32(Keys.General.ALIGNMENT, alignment)
+
+    def add_file_type(self, ftype: int) -> None:
+        self.add_uint32(Keys.General.FILE_TYPE, ftype)
+
+    def add_name(self, name: str) -> None:
+        self.add_string(Keys.General.NAME, name)
+
     def add_author(self, author: str) -> None:
         self.add_string(Keys.General.AUTHOR, author)
 
     def add_version(self, version: str) -> None:
         self.add_string(Keys.General.VERSION, version)
 
-    def add_tensor_data_layout(self, layout: str) -> None:
-        self.add_string(Keys.LLM.TENSOR_DATA_LAYOUT.format(arch=self.arch), layout)
+    def add_organization(self, organization: str) -> None:
+        self.add_string(Keys.General.ORGANIZATION, organization)
 
-    def add_url(self, url: str) -> None:
-        self.add_string(Keys.General.URL, url)
+    def add_finetune(self, finetune: str) -> None:
+        self.add_string(Keys.General.FINETUNE, finetune)
+
+    def add_basename(self, basename: str) -> None:
+        self.add_string(Keys.General.BASENAME, basename)
 
     def add_description(self, description: str) -> None:
         self.add_string(Keys.General.DESCRIPTION, description)
 
-    def add_licence(self, licence: str) -> None:
-        self.add_string(Keys.General.LICENSE, licence)
+    def add_quantized_by(self, quantized: str) -> None:
+        self.add_string(Keys.General.QUANTIZED_BY, quantized)
+
+    def add_size_label(self, size_label: str) -> None:
+        self.add_string(Keys.General.SIZE_LABEL, size_label)
+
+    def add_license(self, license: str) -> None:
+        self.add_string(Keys.General.LICENSE, license)
+
+    def add_license_name(self, license: str) -> None:
+        self.add_string(Keys.General.LICENSE_NAME, license)
+
+    def add_license_link(self, license: str) -> None:
+        self.add_string(Keys.General.LICENSE_LINK, license)
+
+    def add_url(self, url: str) -> None:
+        self.add_string(Keys.General.URL, url)
+
+    def add_doi(self, doi: str) -> None:
+        self.add_string(Keys.General.DOI, doi)
+
+    def add_uuid(self, uuid: str) -> None:
+        self.add_string(Keys.General.UUID, uuid)
+
+    def add_repo_url(self, repo_url: str) -> None:
+        self.add_string(Keys.General.REPO_URL, repo_url)
 
     def add_source_url(self, url: str) -> None:
         self.add_string(Keys.General.SOURCE_URL, url)
 
-    def add_source_hf_repo(self, repo: str) -> None:
-        self.add_string(Keys.General.SOURCE_HF_REPO, repo)
+    def add_source_doi(self, doi: str) -> None:
+        self.add_string(Keys.General.SOURCE_DOI, doi)
 
-    def add_file_type(self, ftype: int) -> None:
-        self.add_uint32(Keys.General.FILE_TYPE, ftype)
+    def add_source_uuid(self, uuid: str) -> None:
+        self.add_string(Keys.General.SOURCE_UUID, uuid)
 
-    def add_name(self, name: str) -> None:
-        self.add_string(Keys.General.NAME, name)
+    def add_source_repo_url(self, repo_url: str) -> None:
+        self.add_string(Keys.General.SOURCE_REPO_URL, repo_url)
 
-    def add_quantization_version(self, quantization_version: int) -> None:
-        self.add_uint32(
-            Keys.General.QUANTIZATION_VERSION, quantization_version)
+    def add_base_model_count(self, source_count: int) -> None:
+        self.add_uint32(Keys.General.BASE_MODEL_COUNT, source_count)
 
-    def add_custom_alignment(self, alignment: int) -> None:
-        self.data_alignment = alignment
-        self.add_uint32(Keys.General.ALIGNMENT, alignment)
+    def add_base_model_name(self, source_id: int, name: str) -> None:
+        self.add_string(Keys.General.BASE_MODEL_NAME.format(id=source_id), name)
+
+    def add_base_model_author(self, source_id: int, author: str) -> None:
+        self.add_string(Keys.General.BASE_MODEL_AUTHOR.format(id=source_id), author)
+
+    def add_base_model_version(self, source_id: int, version: str) -> None:
+        self.add_string(Keys.General.BASE_MODEL_VERSION.format(id=source_id), version)
+
+    def add_base_model_organization(self, source_id: int, organization: str) -> None:
+        self.add_string(Keys.General.BASE_MODEL_ORGANIZATION.format(id=source_id), organization)
+
+    def add_base_model_url(self, source_id: int, url: str) -> None:
+        self.add_string(Keys.General.BASE_MODEL_URL.format(id=source_id), url)
+
+    def add_base_model_doi(self, source_id: int, doi: str) -> None:
+        self.add_string(Keys.General.BASE_MODEL_DOI.format(id=source_id), doi)
+
+    def add_base_model_uuid(self, source_id: int, uuid: str) -> None:
+        self.add_string(Keys.General.BASE_MODEL_UUID.format(id=source_id), uuid)
+
+    def add_base_model_repo_url(self, source_id: int, repo_url: str) -> None:
+        self.add_string(Keys.General.BASE_MODEL_REPO_URL.format(id=source_id), repo_url)
+
+    def add_tags(self, tags: Sequence[str]) -> None:
+        self.add_array(Keys.General.TAGS, tags)
+
+    def add_languages(self, languages: Sequence[str]) -> None:
+        self.add_array(Keys.General.LANGUAGES, languages)
+
+    def add_datasets(self, datasets: Sequence[str]) -> None:
+        self.add_array(Keys.General.DATASETS, datasets)
+
+    def add_tensor_data_layout(self, layout: str) -> None:
+        self.add_string(Keys.LLM.TENSOR_DATA_LAYOUT.format(arch=self.arch), layout)
 
     def add_vocab_size(self, size: int) -> None:
         self.add_uint32(Keys.LLM.VOCAB_SIZE.format(arch=self.arch), size)