Life with AI

Extra episode about Llama 3.

Hey guys, continuing the series of episodes about PEFT, in this episode I talk about inference optimization techniques for LLMs.

I talk about layer pruning, where we prune consecutive layers of the LLM without almost not losing model performance.

I also talk about Mixture of Depths, a similar technique to Mixture of Experts, where we have a router that choses which tokens will be processed in which layer of the LLM.

Paper MoD: ⁠https://arxiv.org/pdf/2404.02258.pdf⁠

Paper layer pruning: ⁠https://arxiv.org/pdf/2403.17887v1.pdf⁠

Instagram of the podcast: https://www.instagram.com/podcast.lifewithai

Linkedin of the podcast: https://www.linkedin.com/company/life-with-ai

Hey guys, this is the first episode in a series of episodes about PEFT, Parameter Efficient Fine Tuning. In this episode I talk about LoRA and QLoRA, two widely used methods that allowed us to fine tune LLMs way faster and in a single GPU without losing performance.

Video sobre QLoRA: ⁠https://www.youtube.com/watch?v=6l8GZDPbFn8⁠

LoRA paper: ⁠https://arxiv.org/pdf/2106.09685.pdf⁠

QLoRA paper: ⁠https://arxiv.org/pdf/2305.14314.pdf⁠

Instagram do podcast: https://www.instagram.com/podcast.lifewithai

Linkedin do podcast: https://www.linkedin.com/company/life-with-ai

Hello, in this episode I talk a Retrieval Aware Fine Tuning (RAFT), a paper that proposes a new technique to use both domain specific fine-tuning and RAG to improve the retrieval capabilities of LLMs.

In the episode I also talk about another paper that is called RAFT, but this time Reward rAnking Fine Tuning, which proposes a new technique to perform RLHF without the convergence problems of Reinforcement Learning.

Retrieval Aware Fine Tuning: https://arxiv.org/abs/2403.10131v1

Reward rAnking Fine Tuning: https://arxiv.org/pdf/2304.06767.pdf

Instagram of the podcast: https://www.instagram.com/podcast.lifewithai

Linkedin of the podcast: https://www.linkedin.com/company/life-with-ai

Hello guys, in this episode I explain how we can scale the context window of an LLM to more than 1M tokens using Ring Attention. In the episode, I also discuss if RAG is dead or not based on these advancements in the context window.

Paper Lost in the Middle: https://arxiv.org/pdf/2307.03172.pdf

Gemini technical report: https://storage.googleapis.com/deepmind-media/gemini/gemini_v1_5_report.pdf

Paper Ring Attention: https://arxiv.org/pdf/2310.01889.pdf

Instagram of the podcast: https://www.instagram.com/podcast.lifewithai

Linkedin of the podcast: https://www.linkedin.com/company/life-with-ai

Hey guys, in the Brazilian version of the Podcast I interviewed Andre, he is an AI expert on IBM and we talked a lot about how to solve problems using AI.

Brains website: https://brains.dev/

Andre's Linkedin: https://www.linkedin.com/in/andrefelipelopes/

Brains' Linkedin: https://www.linkedin.com/company/brains-brazilian-ai-networks/

Instagram of the podcast: https://www.instagram.com/podcast.lifewithai

Linkedin of the podcast: https://www.linkedin.com/company/life-with-ai

Hey guys, in this episode I talk about Mixture Of Experts, more specifically about Mixtral, which is today the best open-source LLM available, and also better than ChatGPT 3.5 and Gemini Pro.

Mixtral paper: ⁠https://arxiv.org/pdf/2401.04088.pdf⁠

Mixtral model: ⁠https://huggingface.co/mistralai/Mixtral-8x7B-v0.1⁠

Mixtral YouTube: ⁠https://www.youtube.com/watch?v=mwO6v4BlgZQ⁠

Instagram: https://www.instagram.com/podcast.lifewithai

Linkedin: https://www.linkedin.com/company/life-with-ai

Hey guys, in this episode I have Sergei as guest and we talked a lot about NLP and Named Entity Recognition (NER). Sergei and his colleagues at NuMind have the current state or the art model for NER and we discussed a lot about it during the episode.

English model: ⁠https://huggingface.co/numind/generic-entity_recognition_NER-v1⁠

Multi-language model: ⁠https://huggingface.co/numind/generic-entity_recognition_NER-multilingual-v1⁠

Sergei's Linkedin: ⁠https://www.linkedin.com/in/svbogdanov/⁠

Instagram: https://www.instagram.com/podcast.lifewithai/  

Linkedin: https://www.linkedin.com/company/life-with-ai

Hey guys, in this episode I explain most of what I know about Transformers. I talk about the architecture, the attention formula, encoder, decoder, self-supervised learning, positional encoding, tokenization, inductive bias, Vision-Transformers, receptive fields...

It was the most technical episode I've recorded so far, and I hope you like it! By the way, it worth listening to this episode with the Transformers paper.

Paper Transformers: ⁠https://arxiv.org/pdf/1706.03762.pdf⁠

Link of OpenAI explaining Next Token Prediction: https://www.linkedin.com/posts/zainhas_the-most-clearest-and-crisp-explanation-ugcPost-7132561633280692224-63AX?utm_source=share&utm_medium=member_desktop

Instagram: https://www.instagram.com/podcast.lifewithai/  

Linkedin: https://www.linkedin.com/company/life-with-ai

Hey guys, in this episode I explain RAG (Retrieval Augmented Generation) and the concept of agents executing different tasks. Hope you like it!

Instagram: https://www.instagram.com/podcast.lifewithai/  

Linkedin: https://www.linkedin.com/company/life-with-ai