Official repo for the paper "Scaling Synthetic Data Creation with 1,000,000,000 Personas"

Magpieという手法とNemotron-4-340B-Instructを用いて合成対話データセットを作るコード

A simple yet powerful tool to turn traditional container/OS images into unprivileged sandboxes.

An Open-source Toolkit for LLM Development

Distribute and run LLMs with a single file.

Nostr client for web.

A bot that summarizes AI papers and posts them on twitter

Ongoing research training Mixture of Expert models.

⏩ Continue is the leading open-source AI code assistant. You can connect any models and any context to build custom autocomplete and chat experiences inside VS Code and JetBrains

Argilla is a collaboration platform for AI engineers and domain experts that require high-quality outputs, full data ownership, and overall efficiency.

Unsupervised text tokenizer for Neural Network-based text generation.

The official implementation of Self-Play Fine-Tuning (SPIN)

0️⃣1️⃣🤗 BitNet-Transformers: Huggingface Transformers Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch with Llama(2) Architecture

Open weights LLM from Google DeepMind.

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

A bagel, with everything.

Robust recipes to align language models with human and AI preferences

Reference implementation for DPO (Direct Preference Optimization)

Train transformer language models with reinforcement learning.

A Comprehensive Assessment of Trustworthiness in GPT Models

Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI

「大規模言語モデル入門」（技術評論社, 2023）のGitHubリポジトリ

Inference Llama 2 in one file of pure C

Fine-tuning LLMs using QLoRA