Transformers in Reinforcement Learning: A Survey A survey that explores the applications of transformers in reinforcement learning. The survey provides a brief overview of RL and challenges of classical RL approaches, traits of transformers that make them suitable for
LLMS
-
Flash Attention: Optimizing Hardware Memory Use and I/O
By
–
Oh yeah, these methods are orthogonal. Flash attention is essentially optimizing hardware memory use and I/O
-
LangChain LLMChain Components: Core Modular Architecture
By
–
Something I was working on at the @agihouse_org hackathon over the weekend The LLMChain (prompt template + llm + output parser) is a core, modular component and is where most customization happens. Understanding this is crucial for understanding LangChain!
-
Flash Attention 2 Integration Reduces Lit-GPT Runtime by 11%
By
–
My colleagues already added Flash Attention 2 to our Lit-GPT repo!
So if you are working on the NeurIPS LLM Efficiency Challenge (for which Lit-GPT is the official starter kit, https://
llm-efficiency-challenge.github.io), you can shave ~11% off your total runtime -
Chainlit: Python Framework for Rapid LLM Application Development
By
–
GitHub – Chainlit/chainlit: Build Python LLM apps in minutes
https://bit.ly/42QIzFn #AI #MachineLearning #DeepLearning #LLMs #DataScience -
GPT-4 Intelligence Phase Transition and Emergence Phenomenon
By
–
The human brain is far to good for the purpose it has evolved. Intelligence might therefore suddenly emerge through some kind of phase transition at some level of complexity. Might something similar have happened to GPT-4? I find it too intelligent for how it is trained.
-
LLaMa Chat Experiment Launches on Perplexity Labs Platform
By
–
Hey Adam! LLaMa Chat is currently an experiment exclusively available on http://
labs.pplx.ai. It’s not available on our mobile apps. Thanks for understanding! -
Open Source LLMs Superior to GPT-4 API for Critical Services
By
–
I am just picturing a case where someone built a crucial service for their company on top of the GPT-4 API . This is a good example why open source LLMs > GPT-4.
-
GPT-4 Degradation and Alternative Model Architectures
By
–
Oh, they made GPT-4 worse … again? Dang. I finally started to find it useful.
Thanks for the reference to Retention, looks like it's orthogonal attempt to RWKV and Hyena? -
What Major AI Developments Happened Last Week?
By
–
Just got back from a week in nature, and wow, it seems like everyone and everything went full steam ahead:
– LLaMA 2
– FlashAttention 2
– …
What else did I miss last week?