You need to agree to share your contact information to access this model
This repository is publicly accessible, but you have to accept the conditions to access its files and content.
Research checkpoints of a speech model trained to refuse requests when an operator instruction tells it to. They are not a safety system. By requesting access you agree to use them for research only.
Log in or Sign Up to review the conditions and access this model content.
duplex-refusal
LoRA adapters for nvidia/personaplex-7b-v1, a full-duplex speech model, that make it refuse a request when a private operator instruction arrives mid-conversation — and answer normally when none does. The instruction is a text span the model reads but never speaks.
Versions
One folder per version; each has its own README with data, recipe, evaluation and known issues.
| version | status | notes |
|---|---|---|
v0.1 |
preview | follows the instruction on held-out questions; known over-refusal, see its README |
Usage
The adapters target PersonaPlex with the depth decoder sliced to 8 codebooks and two extra text
tokens (<instr_start> = 32000, <instr_end> = 32001), so fold them into the base first:
huggingface-cli download MagicLuke/duplex-refusal --include "v0.1/*" --local-dir adapter
python -m duplex_brain.ckpt.build_checkpoint --hf-repo nvidia/personaplex-7b-v1 \
--adapter adapter/v0.1/lora.safetensors --scaling 2.0 --out duplex-refusal-v0.1.safetensors
build_checkpoint is from duplex-brain. Code and
training recipe: duplex-online-if.
- Downloads last month
- -
# Gated model: Login with a HF token with gated access permission hf auth login