Scotch & SOTA 🥃 Pt. 7: Human Feedback Datasets 🫣 - a kirch Collection

kirch 's Collections

Scotch & SOTA 🥃 Pt. 1: Big Boi LLM 🚛

Scotch & SOTA 🥃 Pt. 2: Quantized Small Boi LLM 👉👈

Scotch & SOTA 🥃 Pt. 3: Image Sorcery 🔮

Scotch & SOTA 🥃 Pt. 4: Pre-Training Datasets 📜

Scotch & SOTA 🥃 Pt. 5: Instruction Tuning Datasets 👩‍🏫

Scotch & SOTA 🥃 Pt. 6: Dialogue Tuning Datasets 💬

Scotch & SOTA 🥃 Pt. 7: Human Feedback Datasets 🫣

Scotch & SOTA 🥃 Pt. 4: Multi-Modal 🔀

Scotch & SOTA 🥃 Pt. 7: Human Feedback Datasets 🫣

updated Sep 13, 2023

The elusive “human” feedback

Anthropic/hh-rlhf

Viewer • Updated May 26, 2023 • 169k • 36.6k • 1.73k