LLMS

→ View original post on X — @hwchase17

Quivr: Second Brain AI Project Deep Dive with LangChain

By

@hwchase17

–

04 June 2023 17h07

One of my favorite recent projects is Quivr by @_StanGirard – "your second brain", which utilizes LangChain to store and retrieve unstructured information On the next @langchain Webinar we will try a new format – a deep dive on Quivr. Join us!

→ View original post on X — @nathanbenaich

Language Beyond Token Prediction: Intent and Purpose

By

@nathanbenaich

–

04 June 2023 16h45

“Chiang believes that language without the intention, emotion and purpose that humans bring to it becomes meaningless. “Language is a way of facilitating interactions with other beings. That is entirely different than the sort of next-token prediction, which is what we have

SQL-PaLM: LLM-based Text-to-SQL Achieves State-of-the-Art

By

–

04 June 2023 16h27

9/ SQL-PaLM – an LLM-based Text-to-SQL adopted from PaLM-2; achieves SoTA in both in-context learning and fine-tuning settings; the few-shot model outperforms the previous fine-tuned SoTA by 3.8% on the Spider benchmark.

CodeTF: Open-Source Transformer Library for Code LLMs

By

–

04 June 2023 16h27

10/ CodeTF – an open-source Transformer library for state-of-the-art code LLMs; supports pretrained code LLMs and popular code benchmarks, including standard methods to train and serve code LLMs efficiently.

Direct Preference Optimization: Training LLMs Without RLHF

By

–

04 June 2023 16h27

8/ Direct Preference Optimization – while helpful to train safe & useful LLMs, RLHF can be complex and often unstable; this work proposes an approach to finetune LMs by solving a classification problem on the human preferences data, with no RL required.https://t.co/DZ0GSarfuT
— DAIR.AI (@dair_ai) 4 juin 2023

8/ Direct Preference Optimization – while helpful to train safe & useful LLMs, RLHF can be complex and often unstable; this work proposes an approach to finetune LMs by solving a classification problem on the human preferences data, with no RL required.

Thought Cloning: Learning to Think While Acting

By

–

04 June 2023 16h27

4/ Thought Cloning – introduces an imitation learning framework to learn to think while acting; the idea is not only to clone the behaviors of human demonstrators but also the thoughts humans have when performing behaviors.

Memory-Efficient Fine-Tuning Large Language Models

By

–

04 June 2023 16h27

5/ Fine-Tuning Language Models with Just Forward Passes – proposes a memory-efficient zeroth-order optimizer and a corresponding SGD algorithm to finetune large LMs with the same memory footprint as inference.

→ View original post on X — @mustafasuleyman

Turing Test Results: Bots Fooling Humans 40% of the Time

By

@mustafasuleyman

–

04 June 2023 13h41

turing test results: in 2m conversations, people speaking to a bot thought it was a human 40% of the time. impressive, but a long way to go https://
ai21.com/blog/human-or-
not-results
…