LLaMA 2
An open-weights model from Meta that DeepSeek paid attention to, influencing their approach.
Common Themes
Videos Mentioning LLaMA 2
All-In Summit: Bill Gurley presents 2,851 Miles
All-In Podcast
An AI model developed by Meta, seen as a significant development and potential threat to established tech companies.
Training Llama 2, 3 & 4: The Path to Open Source AGI — with Thomas Scialom of Meta AI
Latent Space
Meta AI's second-generation large language model, a priority project that focused on instruction following and chat capabilities.
![[LLM Paper Club] Llama 3.1 Paper: The Llama Family of Models](https://i.ytimg.com/vi/TgLSYIBoX5U/maxresdefault.jpg)
[LLM Paper Club] Llama 3.1 Paper: The Llama Family of Models
Latent Space
Previous version of Meta's large language model, noted for intentionally not focusing on code generation initially.
E169: Elon sues OpenAI, Apple's decline, TikTok ban, Bitcoin $100K?, Science corner: Microplastics
All-In Podcast
An open-source large language model, specifically the 70B parameter version, supported by Groq's platform.
E143: Nvidia smashes earnings, Arm walks the plank, M&A market, Vivek dominates GOP debate & more
All-In Podcast
An open-source large language model developed by Meta, mentioned as an example of big companies making advanced models freely available, which is good for startups.
This World Does Not Exist — Joscha Bach, Karan Malhotra, Rob Haisfield (WorldSim, WebSim, Liquid AI)
Latent Space
A large language model, whose C implementation by Andrej Karpathy was translated by Devin AI.
Breaking down the OG GPT Paper by Alec Radford
Latent Space
Mentioned as an example of a large language model that can be continuously pre-trained on domain-specific data.
Jared Kushner: Israel-Hamas War, paths forward, macro picture, AI
All-In Podcast
An open-source language model, used as a benchmark for Kai-Fu Lee's model and Grok.
E152: Real estate chaos, WeWork bankruptcy, Biden regulates AI, Ukraine's “Cronkite Moment” & more
All-In Podcast
An open-source AI model from Meta, mentioned with limitations regarding user thresholds before requiring Facebook's involvement.
![[Paper Club] Upcycling Large Language Models into Mixture of Experts](https://i.ytimg.com/vi/e_mkhFkKPEk/maxresdefault.jpg)
[Paper Club] Upcycling Large Language Models into Mixture of Experts
Latent Space
Mentioned in the context of fine-tuning and comparing cosine similarity with upcycled models.
Personal AI Meetup - Bee, BasedHardware, LangChain LangFriend, Deepgram EmilyAI
Latent Space
An LLM model that some customers run on their own infrastructure to minimize network latency.
All-In Summit: In conversation with Vinod Khosla
All-In Podcast
A large language model from Meta that the company is reportedly trying to enhance.
Open Source AI is AI we can Trust — with Soumith Chintala of Meta AI
Latent Space
The second generation of Meta's open-source LLaMA models, with which Soumith Chintala was more closely involved.
A Brief History of the Open Source AI Hacker - with Ben Firshman of Replicate
Latent Space
A large language model released by Meta, which significantly drove growth for Replicate due to its open nature and trainability.
The State of AI in production — with David Hsu of Retool
Latent Space
Mentioned as an open-source model that currently lags behind GPT-4 in performance, leading customers to prefer hosted models.
The Four Wars of the AI Stack - Dec 2023 Recap
Latent Space
A model that people are focusing on fine-tuning.
The Origin and Future of RLHF: the secret ingredient for ChatGPT - with Nathan Lambert
Latent Space
Meta's language model, whose paper cited the effectiveness of RLHF and noted the surprise of NLP researchers at its utility, highlighting its cost and time effectiveness. Used rejection sampling for RLHF process.
Beating GPT-4 with Open Source Models - with Michael Royzen of Phind
Latent Space
The second generation of Meta AI's LLaMA large language models, serving as the foundation for Phind's own fine-tuned models.
Why AI Agents Don't Work (yet) - with Kanjun Qiu of Imbue
Latent Space
A large language model from Meta AI, used as an example for the cost of data labeling versus compute.
The End of Finetuning — with Jeremy Howard of Fast.ai
Latent Space
The base model for Code Llama, which was fine-tuned by Meta.
RAG is a hack - with Jerry Liu of LlamaIndex
Latent Space
A popular open-source model that LlamaIndex integrates with, allowing for self-hosting deployments.
FlashAttention-2: Making Transformers 800% faster AND exact
Latent Space
Meta's latest large language model, released with less restrictive licensing, promoting wider business use and fine-tuning.
"OpenAI is Not God” - The DeepSeek Documentary on Liang Wenfeng, R1 and What's Next
AI Explained
An open-weights model from Meta that DeepSeek paid attention to, influencing their approach.
Marc Benioff | All-In Summit 2024
All-In Podcast
An open-source large language model developed by Meta AI, mentioned as a potential foundation model for custom AI development.