Oh yes it's the nice "Augmenting Self-attention with Persistent Memory" – section 4 – "Feedforward sublayer as an attention layer" 🙂
LLMS
-
Simplified Transformer Architecture with Unified Block Design
By
–
TLDR: A much simpler Transformer with a single type of block wired up to a residual pathway in both parallel and in series is possible but to my knowledge has not yet been convincingly demonstrated. Bit more detail @ https://
github.com/karpathy/rando
mfun/blob/master/transformer_unify.ipynb
… -

Transformer Block Unification: MLP and Attention Similarity
By
–
Random quick note on Transformer block unification. People are usually a bit surprised that the MLP and Attention blocks that repeat in a Transformer can be re-formated to look very similar, likely unifiable. The MLP block just attends over data-independent {key: value} nodes:
-
Eleven Labs: Most Realistic AI Text-to-Voice Platform, Free to Try
By
–
Eleven Labs has the most realistic AI text-to-voice platform I’ve seen. https://t.co/W2WkoSQBRV (free to try)
— AI Breakfast (@AiBreakfast) 28 janvier 2023
It’s 99% perfect. Generates great inflection, cadence, and natural pauses.
Sample: pic.twitter.com/nf0agi4QTKEleven Labs has the most realistic AI text-to-voice platform I’ve seen. http://
beta.elevenlabs.io (free to try) It’s 99% perfect. Generates great inflection, cadence, and natural pauses. Sample: -
Top 10 AI Tools and Frameworks You Need to Know
By
–
#AI https://
analyticsinsight.net/top-10-ai-tool
s-and-frameworks-you-need-to-know-in-2023/
… -
Ted Lieu Introduces AI Regulation Resolution Written by ChatGPT
By
–
Rep. Ted Lieu introduced a resolution calling on Congress to regulate artificial intelligence. The bill was written by the popular online #AI chatbot #ChatGPT. https://
nbcnews.com/politics/congr
ess/ted-lieu-artificial-intelligence-bill-congress-chatgpt-rcna67752
… #ML #DYK #iot #ArtificialIntelligence #MachineLearning #MWC23 (via @JulieNBCNews) #aiethics -
Loading LangChain Agents with Self-Ask Search Tool
By
–
To load agents: “`
from langchain.agents import initialize_agent agent = initialize_agent(tools, llm, agent="lc://agents/self-ask-with-search/agent.json")
“` Documentation: https://
langchain.readthedocs.io/en/latest/modu
les/agents/examples/load_from_hub.html
… -
LangChain SQL Agent Variants with Custom Parameters
By
–
This makes it possible upload chains/agents that are variants of existing chains/agents but with different parameters For example, here's an agent specifically instructed to interact with SQL databases that @fpingham came up with: https://
github.com/hwchase17/lang
chain-hub/tree/master/agents/zero-shot-react-sql
… -
Loading Chains with LangChain Framework
By
–
To load chains: “`
from langchain.chains import load_chain chain = load_chain('lc://chains/path/to/file.json')
“` Documentation: https://
langchain.readthedocs.io/en/latest/modu
les/chains/generic/from_hub.html
… -
Smart Companies Win Big With AI Adoption
By
–
All In On AI: How Smart Companies Win Big With #AI AI has been hitting the headlines recently, two tools – the large language model chatbot #ChatGPT and image generator #Dall-E – have caused a big stir since launching as public betas in recent months. https://
forbes.com/sites/bernardm
arr/2023/01/27/all-in-on-ai-how-smart-companies-win-big-with-artificial-intelligence/
…