Cascade Speculative Drafting for Even Faster LLM Inference Chen et al.: https://
arxiv.org/abs/2312.11462 #ArtificialIntelligence #DeepLearning #MachineLearning
MACHINE LEARNING
-
Cascade Speculative Drafting Accelerates LLM Inference Speed
By
–
-
Technical Report: Gemma Model by DeepMind Released
By
–
Technical report: https://
storage.googleapis.com/deepmind-media
/gemma/gemma-report.pdf
… -
Technical critique of LLM data poisoning and safety guardrails
By
–
Parler d’empoisonnement sur des modèles comme chatGPT c’est très précipiter (voir juste faux) surtout quand on connaît les gardes fous mis sur les feedbacks Plus aucune boîte sérieuse ne met de retraining automatique qui impliquerait du poisoning.
-
Google Introduces Gemma: New State-of-the-Art Open Models
By
–
Exciting news for fellow developers! Gemma: Introducing new state-of-the-art open models @google blog.google/technology/devel… #GoogleAI #AI #ml #DataScience #Google
→ View original post on X — @officialvinita, 2024-02-21 13:47 UTC
-
Enhance Open-Source LLMs Quality Data Few-Shot Prompting
By
–
Improve open-source #LLMs with quality data, few-shot prompting, stacking, and merging — @AbacusAI is leading the way with these innovations: https://
blog.abacus.ai/blog/2024/01/1
1/the-open-source-cookbook-how-to-soup-up-your-open-source-llm/
…
————
#AI #MachineLearning #DeepLearning #DataScience ————
Learn more from @bindureddy … -
New HF Space for visualizing chunk splitting methods in RAG
By
–
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! -
Sequencing Costs Plummet, Accelerating AI-Driven Medical Breakthroughs
By
–
Therapeutic breakthroughs & new insights are rising because the costs of sequencing are plummeting. The trajectories of technologies like AI and bio are stark and powerful. Read them and we read the future. https://
globalxetfs.com/charting-disru
ption-medical-breakthroughs/
… -
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.
-
AI Agents Reasoning Code at Scale GTC24
By
–
Discover the next wave of #AI on Wednesday, March 20 at #GTC24. Join @imbue_ai CEO Kanjun Qiu and NVIDIA VP of Applied Deep Learning Research Bryan Catanzaro for a discussion on AI agents that reason code at scale. https://
nvda.ws/48jEAEm