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

convert-*.py: quantized_by in model card is not relevant for converted gguf

Browse source
This commit is contained in:
brian khuu 2024-07-14 12:00:59 +10:00
parent 9954b64862
commit abc351c270
1 changed files with 0 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

4
gguf-py/gguf/metadata.py
View file

@ -236,10 +236,6 @@ class Metadata:
base_model["repo_url"] = f"https://huggingface.co/{org_component}/{model_full_name_component}"
metadata.base_models.append(base_model)
if "quantized_by" in model_card and metadata.quantized_by is None:
# Not part of hugging face model card standard, but is used by TheBloke to credit them self for quantizing 3rd party models
metadata.quantized_by = model_card.get("quantized_by")
if "license" in model_card and metadata.license is None:
metadata.license = model_card.get("license")