LLMS

→ View original post on X — @flowiseai

Flowise v1.4.3 Release: New APIs, Claude 2.1 and MongoDB Support

By

@flowiseai

–

24 November 2023 20h06

Friday release time
Flowise v1.4.3 freshly baked with: Upsert API Moderation Claude 2.1 support Langfuse User Tracing Vectara QA Chain MongoDB Atlas Chatflow UI/UX

→ View original post on X — @ylecun

LLM Reliability: Replacing Auto-Regressive Prediction with Planning

By

@ylecun

–

24 November 2023 20h02

Please ignore the deluge of complete nonsense about Q*.
One of the main challenges to improve LLM reliability is to replace Auto-Regressive token prediction with planning. Pretty much every top lab (FAIR, DeepMind, OpenAI etc) is working on that and some have already published

LLM Fine-Tuning: Deep Dive Video Tutorial

By

–

24 November 2023 20h00

Dive into LLM fine-tuning in my recent video: https://
youtu.be/7mOD9kgqRf0

Fine-tuning and RAG: Improving AI Reliability and Reducing Hallucinations

By

–

24 November 2023 20h00

Fine-tuning helps but isn't a cure-all for AI issues, such as occasional 'hallucinations'. It improves knowledge robustness, and combining it with methods like Retrieval Augmented Generation (RAG) can increase the accuracy and reliability of your models.

Specificity Improves Language Models for Finance and Medical Tasks

By

–

24 November 2023 20h00

Specificity enhances complex tasks, like updating a language model with finance data for better financial advice, or medical info for improved health responses.

Fine-Tuning Large Language Models: From Generalists to Specialists

By

–

24 November 2023 20h00

The Art of Fine-Tuning Large Language Models… Fine-tuning transforms large language models like GPT-4 from generalists to specialists, like going from a broad education to a PhD, enabling expert-level performance in fields like medicine or finance.

→ View original post on X — @ylecun

Foundation Models Regulation Debate: Open Source vs Big Tech

By

@ylecun

–

24 November 2023 19h53

Max, how many times do we have to repeat that the main disagreement is about *foundation models* particularly *open source* ones. The ones who do want broad regulations are Google, OpenAI, Anthropic, and a few EA-funded doomer institutes like your FLI. The ones who don't want

→ View original post on X — @clementdelangue

Weekly trending AI papers datasets models and spaces

By

@clementdelangue

–

24 November 2023 18h12

Trending papers (
http://
hf.co/papers), datasets (
http://
hf.co/datasets), spaces (
http://
hf.co/spaces) and models (
http://
hf.co/models) of the week on ! Text to Video, Audio & reinforcement learning (hi Q!) is all the rage! Follow me on HF to get my latest

→ View original post on X — @groqinc

Jonathan Ross interviews about Meta’s Llama2-70B versus Bunny llama

By

@groqinc

–

24 November 2023 17h45

Flashback Friday to @JonathanRoss321
's interview with @furrier and @SavIsSavvy at @theCUBE and their discussion about Meta's Llama2-70B model versus Bunny the llama #GroqOn #grok