Published Aug 4, 2023

702: Llama 2 — It's Time to Upgrade your Open-Source LLM — with Jon Krohn (@JonKrohnLearns)

Jon Krohn delves into Meta's Llama 2, an advanced open-source language model that competes with commercial giants through features like time awareness and a unique two-stage reinforcement learning process, while also identifying its current limitations with code and math tasks.

Episode Highlights

Topics covered

Popular Clips

Episode Highlights

Related Episodes

824: Llama 3.2: Open-Source Edge and Multimodal LLMs — with Jon Krohn (@JonKrohnLearns)
Answers 383 questions
806: Llama 3.1 405B: The First Open-Source Frontier LLM — with Jon Krohn (@JonKrohnLearns)
Answers 383 questions
712: Code Llama — with Jon Krohn (@JonKrohnLearns)
Answers 383 questions
713: Llama 2, Toolformer and BLOOM: Open-Source LLMs — with Meta's Dr. Thomas Scialom
Answers 383 questions
670: LLaMA: GPT-3 performance, 10x smaller — with Jon Krohn (@JonKrohnLearns)
Answers 383 questions
672: Open-source "ChatGPT": Alpaca, Vicuña, GPT4All-J, and Dolly 2.0 — with @JonKrohnLearns
Answers 383 questions
707: Vicuña, Gorilla, Chatbot Arena and Socially Beneficial LLMs — with Prof. Joey Gonzalez
Answers 383 questions
772: In Case You Missed It in March 2024 — with Jon Krohn (@JonKrohnLearns)
Answers 383 questions
704: Jon’s “Generative A.I. with LLMs” Hands-on Training — with Jon Krohn (@JonKrohnLearns)
Answers 383 questions
640: What I Learned in 2022 — with Jon Krohn (@JonKrohnLearns)
Answers 383 questions
678: StableLM: Open-source "ChatGPT"-like LLMs you can fit on one GPU — with @JonKrohnLearns
Answers 383 questions
787: MLOps: The Job and The Key Tools — with Demetrios Brinkmann
Answers 383 questions
788: Multi-Agent Systems: How Teams of LLMs Excel at Complex Tasks — with @JonKrohnLearns
Answers 383 questions
666: GPT-4 — with Jon Krohn (@JonKrohnLearns)
Answers 383 questions
728: Use Contrastive Search to get Human-Quality LLM Outputs — with Jon Krohn (@JonKrohnLearns)
Answers 383 questions

Dexa/Super Data Science: ML & AI Podcast with Jon Krohn

702: Llama 2 — It's Time to Upgrade your Open-Source LLM — with Jon Krohn (@JonKrohnLearns)

Topics covered

Popular Clips

Llama Two Insights

Llama 2 Insights

Llama Two Insights

Episode Highlights

Model Overview

Performance and Metrics

Innovative Features

Related Episodes

824: Llama 3.2: Open-Source Edge and Multimodal LLMs — with Jon Krohn (@JonKrohnLearns)

806: Llama 3.1 405B: The First Open-Source Frontier LLM — with Jon Krohn (@JonKrohnLearns)

712: Code Llama — with Jon Krohn (@JonKrohnLearns)

713: Llama 2, Toolformer and BLOOM: Open-Source LLMs — with Meta's Dr. Thomas Scialom

670: LLaMA: GPT-3 performance, 10x smaller — with Jon Krohn (@JonKrohnLearns)

672: Open-source "ChatGPT": Alpaca, Vicuña, GPT4All-J, and Dolly 2.0 — with @JonKrohnLearns

707: Vicuña, Gorilla, Chatbot Arena and Socially Beneficial LLMs — with Prof. Joey Gonzalez

772: In Case You Missed It in March 2024 — with Jon Krohn (@JonKrohnLearns)

704: Jon’s “Generative A.I. with LLMs” Hands-on Training — with Jon Krohn (@JonKrohnLearns)

640: What I Learned in 2022 — with Jon Krohn (@JonKrohnLearns)

678: StableLM: Open-source "ChatGPT"-like LLMs you can fit on one GPU — with @JonKrohnLearns

787: MLOps: The Job and The Key Tools — with Demetrios Brinkmann

788: Multi-Agent Systems: How Teams of LLMs Excel at Complex Tasks — with @JonKrohnLearns

666: GPT-4 — with Jon Krohn (@JonKrohnLearns)

728: Use Contrastive Search to get Human-Quality LLM Outputs — with Jon Krohn (@JonKrohnLearns)

702: Llama 2 — It's Time to Upgrade your Open-Source LLM — with Jon Krohn (@JonKrohnLearns)

Topics covered

Popular Clips

Episode Highlights

Model OverviewJon Krohn explores Meta's Llama 2, an open-source large language model with commercial potential and advanced features. He discusses its model variety, immense capacity, and innovative time awareness feature, highlighting its groundbreaking two-stage RLHF approach.

Model Overview

Performance and Metrics

Innovative FeaturesLlama 2, Meta's latest open-source large language model, showcases innovative features like time awareness and a two-stage reinforcement learning process. These advancements position it as a leading competitor in the open-source LLM space, rivaling even commercial models.

Innovative Features

Related Episodes