2/ Links For those who are eager, you can check out the code and video tutorial at the links below: Youtube: https://
youtube.com/watch?t=625
Python: https://
github.com/langchain-ai/l
anggraph/blob/main/examples/lats/lats.ipynb
… Thanks to @hinthornw for the implementation.
LLMS
-
LangGraph LATS Implementation Code and Video Tutorial Released
By
–
-
NVIDIA AI Enterprise Streamlines GenAI Development and LLM Inference
By
–
Learn how NVIDIA AI Enterprise enables enterprises to streamline #genAI development, accelerate #LLM inference, and enhance security and manageability with a full stack software solution. #GTC24 Register now. https://
nvda.ws/49KSsZs -
Autonomous Agents vs Diffusion Transformer Models
By
–
autonomous agent will be better than diffusion + transformer model
-
Karpathy releases tokenization tutorial covering UTF-8 and byte pair encoding
By
–
ICYMI – Andrej Karpathy has released an excellent video tutorial on "Tokenization" couple of days back. ⦿ Basics covered: Strings, Unicode code points, and encodings like UTF-8.
⦿ Byte pair encoding algorithm explained and implemented in Python.
⦿ Delving into complexities: -
Gemini 1.5 Achieves 10M Context Token Capacity
By
–
Gemini 1.5 can do 10M context tokens actually, so it's > than Magic's model. https://
blog.google/technology/ai/
google-gemini-next-generation-model-february-2024/#context-window
… -
Moonshot AI raises $1B at $2.5B valuation from Alibaba
By
–
Chinese startup Moonshot AI raised over $1B at a $2.5B valuation from backers including Alibaba.
— Rowan Cheung (@rowancheung) 23 février 2024
The startup focuses on the development of LLMs handling long-form text and has a ChatGPT alternative called 'Kimi Chat'.
China's AI has been accelerating.https://t.co/Ls7OLFUfvLChinese startup Moonshot AI raised over $1B at a $2.5B valuation from backers including Alibaba. The startup focuses on the development of LLMs handling long-form text and has a ChatGPT alternative called 'Kimi Chat'. China's AI has been accelerating.
-
Magic AI Startup Achieves Major Breakthrough in Active Reasoning
By
–
Magic, a startup building AI coding “coworkers”, claims to have made a massive AI breakthrough. The startup claims its model now can ingest up to 3.5M words (nearly 5x Gemini 1.5) and made an ‘active reasoning’ breakthrough reminiscent of OpenAI's Q*.
-
Google’s AI Launches Overshadowed by OpenAI Competition
By
–
Google's been having a rough month. Last week’s Gemini 1.5 breakthrough? Overshadowed by OpenAI’s Sora. And now, their release of Gemma, a new open-source family of AI models, was dwarfed by the backlash. Tough for Google's PR/marketing team.
-
Mistral and MLX for Local AI Model Deployment
By
–
Either that or just mistral. Locally using MLX, I already did a few!
-
Excitement Growing for Favorite LLM Evolution
By
–
Thanks for making this! I am excited to see it evolve even more. Definitely one of my favorite LLMs at the moment.