Beyond Chinchilla-Optimal: Accounting for Inference in Language Model Scaling Laws Nikhil Sardana, Jonathan Frankle : https://
arxiv.org/abs/2401.00448 #Artificialintelligence #DeepLearning #MachineLearning
LLMS
-
Scaling Laws Beyond Chinchilla: Inference Optimization
By
–
-
Groq Demonstrates Shakespeare Translation Speed with Advanced LLM
By
–
Groq on the Bard, see how our token in & out speed handles summarization of Shakespeare's complex #language into today's english & for fun see how the Bard #LLM handles the sample request. 3 min vid on sys-prompt your #llm at #groqspeed. https://
youtu.be/nGbZSrC1ZEs
#learn #GenAI -
2023 Summary: Gemini Neural Networks and AI Progress
By
–
Hi 2024! Summary of 2023 for many of the people I love working with: Gemini May 2024 bring us more capable Neural Networks, loss functions converge quickly, and may we never see an Inf or a NaN
-
@aibreakfast — 2024-01-01
By
–
Microsoft Copilot just launched their iOS app, which gives you GPT-4 and DALL-E 3 on your smartphone for free: https://
apps.apple.com/us/app/microso
ft-copilot/id6472538445
… -
Llama 2 70B on Groq LPU Delivers Fast Cocktail Recipes NYE
By
–
Side-by-side, #Llama 2, 70B on the Groq LPU™ Inference Engine and the @lmsysorg. If you have to become an instant bartender for your #NYE #party tonight, #prompt for some cocktail & mocktail recipes at https://t.co/4FkcJN9SgW learn on the go. #GenAI #LLMs #groqspeed #inference pic.twitter.com/OUnHeFIYGS
— Groq Inc (@GroqInc) 31 décembre 2023Side-by-side, #Llama 2, 70B on the Groq LPU™ Inference Engine and the @lmsysorg
. If you have to become an instant bartender for your #NYE #party tonight, #prompt for some cocktail & mocktail recipes at http://
Groq.com learn on the go. #GenAI #LLMs #groqspeed #inference -
Evaluating RAG Pipelines with LangChain and RAGAS
By
–
Evaluating RAG pipelines using LangChain and Ragas LangChain can help you build RAG pipelines, but how do you evaluate them? We have a great integration with RAGAS to do exactly that! h/t @DataScienceHarp for writing all about it Blog: https://
deci.ai/blog/evaluatin
g-rag-pipelines-using-langchain-and-ragas/
… -
LLaRA: Adapting LLMs for Dense Retrieval Tasks
By
–
9/ Making LLMs Better at Dense Retrieval – proposes LLaRA which adapts an LLM for dense retrieval; LLaMa-2-7B was improved on benchmarks like MSMARCO and BEIR.
-
Gemini vs GPT-4V: Vision-Language Models Comparison
By
–
10/ Gemini vs. GPT-4V – a comparison of vision-language models like Gemini & GPT-4V; finds that GPT-4V is precise and succinct in responses, while Gemini excels in providing detailed, expansive answers accompanied by relevant imagery and links.
-
26 Principles for Optimizing LLM Prompts and Instructions
By
–
7/ Principled Instructions Are All You Need – introduces 26 principles to streamline the process of querying and prompting LLMs; conducts extensive experiments on LLaMA-1/2 & GPT-3.5/4 to verify their effectiveness on instructions & prompts design.
-
Survey of Reasoning with Foundation Models: Latest Advancements
By
–
8/ A Survey of Reasoning with Foundation Models – provides a comprehensive survey of seminal foundational models for reasoning, highlighting the latest advancements in various reasoning tasks, methods, benchmarks, and potential future directions.