From 916872f72f19912582297dd4d3da41f027504b82 Mon Sep 17 00:00:00 2001
From: brian khuu <mofosyne@gmail.com>
Date: Fri, 31 May 2024 14:19:53 +1000
Subject: [PATCH] convert-*.py: model card metadata

---
 convert_hf_to_gguf.py   | 24 ++++++++++++++++++++----
 gguf-py/gguf/utility.py | 10 +++++-----
 2 files changed, 25 insertions(+), 9 deletions(-)

diff --git a/convert_hf_to_gguf.py b/convert_hf_to_gguf.py
index a79898350..9fe81d1a2 100755
--- a/convert_hf_to_gguf.py
+++ b/convert_hf_to_gguf.py
@@ -10,6 +10,7 @@ import json
 import os
 import re
 import sys
+import frontmatter
 from enum import IntEnum
 from pathlib import Path
 from hashlib import sha256
@@ -96,6 +97,7 @@ class Model:
     lazy: bool
     part_names: list[str]
     is_safetensors: bool
+    model_card: dict[str, Any]
     hparams: dict[str, Any]
     block_count: int
     tensor_map: gguf.TensorNameMap
@@ -123,6 +125,7 @@ class Model:
         self.is_safetensors = len(self.part_names) > 0
         if not self.is_safetensors:
             self.part_names = Model.get_model_part_names(self.dir_model, "pytorch_model", ".bin")
+        self.model_card = Model.load_model_card(dir_model)
         self.hparams = Model.load_hparams(self.dir_model)
         self.block_count = self.find_hparam(["n_layers", "num_hidden_layers", "n_layer", "num_layers"])
         self.tensor_map = gguf.get_tensor_name_map(self.model_arch, self.block_count)
@@ -148,10 +151,18 @@ class Model:
         self.gguf_writer = gguf.GGUFWriter(path=None, arch=gguf.MODEL_ARCH_NAMES[self.model_arch], endianess=self.endianess, use_temp_file=self.use_temp_file,
                                            split_max_tensors=split_max_tensors, split_max_size=split_max_size, dry_run=dry_run, small_first_shard=small_first_shard)
 
-        # Update any missing authorship metadata with huggingface_parameters
-        if self.metadata is not None and self.metadata.source_hf_repo is None:
-            if self.hparams is not None and "_name_or_path" in self.hparams:
-                self.metadata.source_hf_repo = self.hparams["_name_or_path"]
+        # Update any missing authorship metadata with HuggingFace parameters or model card frontmatter
+        if self.metadata is not None:
+
+            # Source Hugging Face Repository
+            if self.metadata.source_hf_repo is None:
+                if self.hparams is not None and "_name_or_path" in self.hparams:
+                    self.metadata.source_hf_repo = self.hparams["_name_or_path"]
+
+            # Model License
+            if self.metadata.license is None:
+                if self.model_card is not None and "license" in self.model_card:
+                    self.metadata.source_hf_repo = self.model_card["license"]
 
         # Set model name based on latest metadata either provided or calculated from environment
         def get_model_name(metadata, huggingface_parameters, dir_model, model_arch):
@@ -499,6 +510,11 @@ class Model:
 
         return part_names
 
+    @staticmethod
+    def load_model_card(dir_model: Path):
+        with open(dir_model / "README.md", "r", encoding="utf-8") as f:
+            return frontmatter.load(f)
+
     @staticmethod
     def load_hparams(dir_model: Path):
         with open(dir_model / "config.json", "r", encoding="utf-8") as f:
diff --git a/gguf-py/gguf/utility.py b/gguf-py/gguf/utility.py
index dd08a36d2..0919a744e 100644
--- a/gguf-py/gguf/utility.py
+++ b/gguf-py/gguf/utility.py
@@ -29,9 +29,9 @@ def naming_convention(model_name: str, base_name: str, finetune_string:str, vers
     # Reference: https://github.com/ggerganov/ggml/blob/master/docs/gguf.md#gguf-naming-convention
 
     if base_name is not None:
-        name = base_name.strip().title().replace(' ', '_')
+        name = base_name.strip().title().replace(' ', '-')
     elif model_name is not None:
-        name = model_name.strip().title().replace(' ', '_')
+        name = model_name.strip().title().replace(' ', '-')
     else:
         name = "ggml-model"
 
@@ -41,10 +41,10 @@ def naming_convention(model_name: str, base_name: str, finetune_string:str, vers
     else:
         parameters = f"-{per_model_rounded_weight_estimate}"
 
-    finetune = f"-{finetune_string.strip().title().replace(' ', '_')}" if finetune_string is not None else ""
+    finetune = f"-{finetune_string.strip().title().replace(' ', '-')}" if finetune_string is not None else ""
 
-    version = f"-{version_string.strip().replace(' ', '_')}" if version_string is not None else ""
+    version = f"-{version_string.strip().replace(' ', '-')}" if version_string is not None else ""
 
-    encoding = f"-{encoding_scheme.strip().replace(' ', '_').upper()}"
+    encoding = f"-{encoding_scheme.strip().replace(' ', '-').upper()}"
 
     return f"{name}{parameters}{finetune}{version}{encoding}"