I've built a new HF Space to let you visualize how different splitting methods affect the chunks you fet for RAG! Try it out here: https://
huggingface.co/spaces/m-ric/c
hunk_visualizer
… It's heavily inspired from @GregKamradt 's http://
chunkviz.com – all credits to him for the idea!
COMPUTING
-
New HF Space for visualizing chunk splitting methods in RAG
By
–
-
Groq’s LPU Hardware Breakthrough Enables Near-Instantaneous LLM Response Times
By
–
Groq's recent hardware breakthroughs have been going viral on X.
— Rowan Cheung (@rowancheung) 21 février 2024
Groq (not Grok) uses LPUs instead of GPUs, allowing the chatbot to run LLMs at nearly instantaneous response times.
This unlocks a whole new world of potential AI and user experiences.pic.twitter.com/EnJnd3jEQmGroq's recent hardware breakthroughs have been going viral on X. Groq (not Grok) uses LPUs instead of GPUs, allowing the chatbot to run LLMs at nearly instantaneous response times. This unlocks a whole new world of potential AI and user experiences.
-
Nous-Hermes-2 Quantized to 4-bit for MLX Apple Silicon
By
–
I just quantized this amazing model to 4-bit, with support for the MLX platform so you can run it super fast on Apple Silicon https://
huggingface.co/mlx-community/
Nous-Hermes-2-Mistral-7B-DPO-4bit-MLX
… -
Metaverse and the Future of Product Interaction
By
–
#Metaverse and the future of product interaction @ExpComputer https://
expresscomputer.in/guest-blogs/me
taverse-and-the-future-of-product-interaction/109317/
… -
Metaverse Games Support 40,000 Simultaneous Players Technology
By
–
#Metaverse Games With 40,000 Players in the Same Space? The Tech Is Coming (via @decryptmedia
) https://
decrypt.co/218189/metaver
se-games-40000-players-tech-coming
… -
Speculative Streaming: Fast LLM Inference Without Auxiliary Models
By
–
Speculative Streaming: Fast LLM Inference without Auxiliary Models Bhendawade et al.: https://
arxiv.org/abs/2402.11131 #ArtificialIntelligence #DeepLearning #MachineLearning -
Multimodal models struggle with transfer learning to text despite image knowledge.
By
–
Also weird there’s no obvious transfer learning back to text. For all the ineffable, AGI-essential knowledge supposedly in images, multimodal models seem no better at spatial reasoning word problems, creating SVGs, designing web UI, or drawing ASCII art.
-
Control Theory and Cybernetics: Technical Definitions Matter
By
–
Control is a technical term (as in control theory, cybernetics etc.). I don't think it's useful if you try to redefine it. Our inferential distance might be too large for meaningful discussion.
-
Digital Proving Ground Shapes Autonomous Vehicle Transportation Future
By
–
Deploying autonomous vehicles requires the adoption of robust and effective policies. At #GTC24, find out how a new digital proving ground will play a pivotal role in shaping the future of transportation.
— NVIDIA AI (@NVIDIAAI) 20 février 2024
Register here: https://t.co/5H8Lv0pvxa pic.twitter.com/DEdORuhZG9Deploying autonomous vehicles requires the adoption of robust and effective policies. At #GTC24, find out how a new digital proving ground will play a pivotal role in shaping the future of transportation. Register here: https://
nvda.ws/3w3AlPD -
Google and its AI: Genius or Failure?
By
–
What is #Google playing at with its AI? Gemini Pro, Gemini Ultra, Advanced… And now Gemini 1.5! Everyone’s calling it genius, but what if it’s a sign of defeat? We break it down in this video → https://youtu.be/K8uk68X7F4I #ArtificialIntelligence #GoogleGemini