-
Notifications
You must be signed in to change notification settings - Fork 6
Open
Description
red-candle only support safetensor models (soon to include GGUF). Many models are in pytorch bin file format (like distilbert/distilbert-base-uncased-finetuned-sst-2-english). I'd like to include instructions on how to convert.
Other variants I'd like to cover AWQ and w4a16 quantization methods.
Metadata
Metadata
Assignees
Labels
No labels