6/ Fast Inference of Mixture-of-Experts – achieves efficient inference of Mixtral-8x7B models through offloading; designs a MoE-specific offloading strategy that enables running Mixtral-8x7B on desktop hardware and free-tier Google Colab instances.
LLMS
-
LLaMA Pro: Post-Pretraining Method Without Catastrophic Forgetting
By
–
4/ LLaMA Pro – proposes a post-pretraining method to improve an LLM’s knowledge without catastrophic forgetting; it achieves this by tuning expanded identity blocks using only new corpus while freezing the inherited blocks.
-
32 Techniques to Mitigate Hallucination in Large Language Models
By
–
2/ Mitigating Hallucination in LLMs – summarizes 32 techniques to mitigate hallucination in LLMs; introduces a taxonomy categorizing methods like RAG, Knowledge Retrieval, CoVe, and more.
-
Top ML Papers of the Week: DocLLM, ALOHA, Fine-tuning
By
–
The Top ML Papers of the Week (Jan 1 – Jan 7): – DocLLM
– Mobile ALOHA
– Self-Play Fine-tuning
– Fast Inference of MoE
– LLM Augmented LLMs
– Mitigating Hallucination in LLMs
… -
GPT-4V LangChain Elasticsearch Handwritten Letter Analysis
By
–
Santa GenAI: Deciphering Handwritten Christmas Letters with LangChain and Elasticsearch Great tutorial from @alexsalgadoprof that: 1. Uses GPT-4V to analyze an image an say whats in it
2. Extracts structured information as JSON from that analysis https://
discuss.elastic.co/t/dec-22nd-202
3-en-santa-claus-meets-genai-deciphering-handwritten-christmas-letters-with-llm-langchain-and-elasticsearch/347311
… -
Generative AI Key Terms Explained: Essential Definitions
By
–
Generative AI Key Terms Explained: This article introduces and explains key terms important to generative AI, and links to additional resources to learn more. https://
kdnuggets.com/generative-ai-
key-terms-explained?utm_source=dlvr.it&utm_medium=twitter&utm_campaign=generative-ai-key-terms-explained
… -
Python ML and LLM tutorials daily learning path
By
–
That's a wrap! If you interested in: – Python – ML/MLOps – CV/NLP – LLMs – AI Engineering Find me → @akshay_pachaar Everyday, I share tutorials on above topics! Cheers!!
-
FunSearch: LLMs Making Mathematical Science Discoveries
By
–
FunSearch: Making new discoveries in mathematical sciences using Large Language Models https://
zurl.co/wZC3 @GoogleDeepMind #AI #DigitalTransformation #FutureOfWork #GenAI #IoT #5G #CES2024 #MWC24 @grattonboy @Paula_Piccard @mvollmer1 @gvalan @enilev -
GPT Evolution: Beyond Stochastic Parrots with Scaling
By
–
GPT-3, GPT-3.5, GPT-4. How blind would you have to be, to look at whatever has increased with the version number, and see only a "stochastic parrot" with a bigger memory?
-
Modified Physics Problem Transformed into a Gotcha Question
By
–
The problem is a modified version of the first problem in Thinking Physics, transformed by me into a gotcha by changing "total miles" to "total hours". I should be quite surprised if that exact problem and its answer was in GPT-4's training set to be memorized.