A repository of links with advice related to grad school applications, research, phd etc

Robust recipes to align language models with human and AI preferences

pdb++, a drop-in replacement for pdb (the Python debugger)

A framework for few-shot evaluation of language models.

A simple unified framework for evaluating LLMs

Code and data for "Lost in the Middle: How Language Models Use Long Contexts"

Prod Env

An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & Mixtral)

[ICLR'24 spotlight] Tool-Augmented Reward Modeling

A recipe for online RLHF and online iterative DPO.

The repository of the project "Fine-tuning Large Language Models with Sequential Instructions", code base comes from open-instruct and LAVIS

Code for the TriviaQA reading comprehension dataset

Automatically literature survey/review with GPT! An intelligent research assistant leveraging GPT-3.5 /GPT-4 to find, analyze, and rank relevant academic papers from Google Scholar based on user-pr…

Code and documentation to train Stanford's Alpaca models, and generate the data.

Aligning pretrained language models with instruction data generated by themselves.

Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step

Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)

Inference code for Llama models

The official Meta Llama 3 GitHub site

A high-throughput and memory-efficient inference and serving engine for LLMs

Implementation of Toolformer, Language Models That Can Use Tools, by MetaAI

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…

Codes for "Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models".

[ICLR 2023] ReAct: Synergizing Reasoning and Acting in Language Models

A snappy, keyboard-centric terminal user interface for interacting with large language models. Chat with ChatGPT, Claude, Llama 3, Phi 3, Mistral, Gemma and more.

ToolQA, a new dataset to evaluate the capabilities of LLMs in answering challenging questions with external tools. It offers two levels (easy/hard) across eight real-life scenarios.