Instructions to use HashNuke/barge-in-detector with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use HashNuke/barge-in-detector with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="HashNuke/barge-in-detector")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("HashNuke/barge-in-detector") model = AutoModelForSequenceClassification.from_pretrained("HashNuke/barge-in-detector", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download AGENTS.md from HashNuke/barge-in-detector: direct link, hf CLI and curl.
- Browser
- Download file 1.1 kB
-
https://huggingface.co/HashNuke/barge-in-detector/resolve/main/AGENTS.md
- Command line
-
hf download hf://HashNuke/barge-in-detector/AGENTS.md
-
curl -L -o AGENTS.md https://huggingface.co/HashNuke/barge-in-detector/resolve/main/AGENTS.md
Model releases only
Canonical development source: https://github.com/vxpipe/barge-in-detector. Keep this repo limited to model weights, tokenizer/configuration, model card, licence/attribution and provenance. Dataset releases belong in HashNuke/barge-in-detector-data. Training data, executable scripts, tests, benchmarks, labnotes and milestones belong in GitHub.
Follow the GitHub AGENTS.md for model contracts, CPU latency/quality gates, the single RTX 5090 training policy, gpubox and verification. Create checkpoint labnotes there using bin/create-labnotes and use labnotes/milestones/index.md; keep the helper and development records in the source repo.
Publish artifacts from a committed source revision. release.json must pin the exact dataset and code commits and artifact hashes. Verify unchanged hashes, public model loading and accurate limitations in the card. Do not publish credentials, local environments or training checkpoints outside a selected release. Use Hub large-file storage for weights/tokenizer. Use ordinary release commits; do not rewrite history, reset or force-push.