Stars
Model components of the Llama Stack APIs
An open-source implementaion for fine-tuning Llama3.2-Vision series by Meta.
Source code for timing related libraries managed by webtiming (multi-device timing CG)
AI driven development in your terminal. Designed for large, real-world tasks.
Official implementation for the paper: "Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering""
Code for paper "LEVER: Learning to Verifiy Language-to-Code Generation with Execution" (ICML'23)
Reference implementation of code generation projects from Facebook AI Research. General toolkit to apply machine learning to code, from dataset creation to model training and evaluation. Comes with…
This is the official code for the paper CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning (NeurIPS22).
This is a collection of research papers for Self-Correcting Large Language Models with Automated Feedback.
CodeUltraFeedback: aligning large language models to coding preferences
Fast and memory-efficient exact attention
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
Efficient LLM inference on Slurm clusters using vLLM.
A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.
Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)
Scripts for fine-tuning Meta Llama with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting…
Customizable implementation of the self-instruct paper.
Finetune Llama 3.2, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)
GPU programming related news and material links
This repo is meant to serve as a guide for Machine Learning/AI technical interviews.