Results for “ssti”

Fine-tune instruction-following LLMs with Unsloth's optimized SFTTrainer, covering dataset formatting, chat templates, training configuration, and thinking-model patterns.

SNLI-VE: Visual Entailment Dataset

Transcribes audio files to text using OpenAI Whisper, optimized for Brazilian Portuguese, with support for common audio formats and timestamped output.

Scans agent skills for security issues including prompt injection, malicious scripts, excessive permissions, secret exposure, and supply chain risks.

Quantifies audio source separation quality by computing the signal-to-distortion ratio (SDR) between ground-truth and estimated stems, with per-stem and record-level averaging.