🤖 LLM - hop1.ng.1357 · Scour

Paper page - Large Language Models Explore by Latent Distilling ✨LLMs

huggingface.co·3h

How to Build Your Own Language-Specific LLM [Full Handbook] ✨LLMs

freecodecamp.org·5d

Network Edge Inference for Large Language Models: Principles, Techniques, and Opportunities ⚡Edge AI

LLMs are the worlds most powerful autocomplete ✨LLMs

alfredvc.no·16h·Hacker News

LaDiR: Latent Diffusion Enhances LLMs for Text Reasoning ✨LLMs

machinelearning.apple.com·1d·Hacker News

Why Model Collapse in LLMs is Inevitable With Self-Learning ✨LLMs

hackaday.com·15h·Hacker News

AmSach/kvquant: Drop-in KV cache compressor for local LLM inference - Run 70B models on 8GB RAM 📱Edge AI Optimization

github.com·5h·DEV

Text Summarization with Scikit-LLM ✨LLMs

machinelearningmastery.com·3d

Large Language Models in Communications ✨LLMs

databricks.com·1d

LLM 0.32a0 is a major backwards-compatible refactor 🪄Prompt Engineering

simonwillison.net·22h·Hacker News

Information Extraction from Electricity Invoices with General-Purpose Large Language Models ✨LLMs

The Recurrent Transformer: Greater Effective Depth and Efficient Decoding (5 minute read) 🖼️Multimodal AI

alphaxiv.org·1d

Show HN: How LLMs Work – Interactive visual guide based on Karpathy's lecture ✨LLMs

ynarwal.github.io·6d·Hacker News

cauchy221/Alignment-Whack-a-Mole-Code: The official code repo of Alignment Whack-a-Mole: Finetuning Activates Verbatim Recall of Copyrighted Books in Large Language Models ✨LLMs

github.com·14h·Hacker News

A Primer on LLM Post-Training ✨LLMs

pytorch.org·2d·Hacker News

Training a Transformer to Compose One Step Per Layer (and Proving It) ✨LLMs

lesswrong.com·3d

Speculative Decoding vs MoE: 3.2x Cost Gap on Llama 3 💉Prompt Injection

tildalice.io·2d

Identifying the Achilles' Heel: An Iterative Method for Dynamically Uncovering Factual Errors in Large Language Models ✨LLMs

epscylonb/1386.ai.rocm: A lightweight transformer language model built from scratch in PyTorch, trained on a single consumer GPU with a full pipeline for data processing, pretraining, and instruction tuning. ⚙️MLOps

github.com·2d·Hacker News

Language Generation in the Limit ✨LLMs

openreview.net·5d

Log in to enable infinite scrolling