mirror of
https://github.com/jamiepine/voicebox.git
synced 2026-09-16 21:30:39 -07:00
James Pine
7a90290a76
TADA hardcodes 'meta-llama/Llama-3.2-1B' as its tokenizer source in both the Aligner and TadaForCausalLM.from_pretrained(). That repo is gated and requires accepting Meta's license on HuggingFace. Monkey-patch AutoTokenizer.from_pretrained during model loading to redirect Llama tokenizer requests to 'unsloth/Llama-3.2-1B', an ungated mirror with identical tokenizer files. The patch is scoped to model loading only and restored immediately after.