Apple Intelligence Foundation Language Models 👉 Paper : https://arxiv.org/pdf/2407.21075 Two models: On-device: ~3B param with task-specific LoRA adapters Server: ~70B (my estimation),...

Awesome Production LLM: Curated Open-Source Libraries Curiosity: What are the best open-source libraries for building production-ready LLM applications? How can we systematically organize tools ac...

Not sure if you chunked your data right to enable optimal context retrieval? Not sure which embedding model will work best for your data? Don’t worry, you’re not alone.. A RAG has several movi...

Unlocking the Power of RLHF in Large Language Models Curiosity: How do LLMs learn to align with human preferences? What is Reinforcement Learning from Human Feedback (RLHF) and how does it work? ...

Accelerating LLMs by 2× with Graph-Structured Speculative Decoding Curiosity: How can we make LLM inference faster? What happens when we use graph structures to optimize speculative decoding? Res...

GPT-4’s Struggle with Long-Context Bilingual Reasoning Curiosity: Despite being one of the leading LLMs, GPT-4 struggles with long-context bilingual reasoning tasks, even with text lengths shorter...

It is extremely important to ensure Data Quality upstream of ML Training and Inference Pipelines, trying to do that in the pipelines will cause unavoidable failure when working at scale. Curiosi...

LLMs Course Github 👉 https://github.com/peremartra/Large-Language-Model-Notebooks-Course/tree/main/3-LangChain Introduction to LangChain and Agents: Building Intelligent Applications Curiosit...

If you want to 𝗹𝗲𝗮𝗿𝗻 in a 𝘀𝘁𝗿𝘂𝗰𝘁𝘂𝗿𝗲𝗱 𝘄𝗮𝘆 to 𝗯𝘂𝗶𝗹𝗱 𝗟𝗟𝗠 𝘀𝘆𝘀𝘁𝗲𝗺𝘀 using good 𝗟𝗟𝗠𝗢𝗽𝘀 principles… We want to announce that we just 𝗿𝗲𝗹𝗲𝗮𝘀𝗲𝗱 𝟴 𝗠𝗲𝗱𝗶𝘂𝗺 𝗹𝗲𝘀𝘀𝗼𝗻𝘀 for the 𝗛𝗮𝗻𝗱𝘀-𝗼𝗻 𝗟𝗟𝗠𝘀 𝗰𝗼𝘂𝗿𝘀𝗲 that will put ...

LLM2Vec: Transform LLMs into Embedding Models Curiosity: Can we transform decoder-only LLMs into powerful text encoders? What happens when we enable bidirectional attention and contrastive learnin...