AI Unplugged | Datta | Substack

AI Unplugged 23: nGPT normalised transformer, LAUREL, TokenFormer

Insights over information

READ THE LATEST

Most Popular

AI Unplugged 20: SCoRE Self Correction via RL, OpenAI o1 models, Qwen 2.5 coder, Spectrum Fine Tuning.

Sep 26, 2024 • Datta, Ashwanth, and Amit Saha

AI Unplugged 21: TPI LLM, Differential Transformer, ARIA, Ministral 3B and 8B

Oct 17, 2024 • Datta, Ashwanth, and Amit Saha

AI Unplugged 19: KTO for model alignment, OLMoE, Mamba in the LlaMa, Plan Search

Sep 12, 2024 • Datta, Ashwanth, and Amit Saha

AI Unplugged 12: MoRA. DPO vs PPO. CoPE Contextual Position Encoding. S3D Self Speculative Decoding.

Jun 6, 2024 • Datta, Ashwanth, and Gavrish Prabhu

AI Unplugged

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts