purang2
Follow
Lists (9)
Stars
Train Llama 2 & 3 on the SQuAD v2 task as an example of how to specialize a generalized (foundation) model.
Train transformer language models with reinforcement learning.
Qwen2 is the large language model series developed by Qwen team, Alibaba Cloud.
Repository for "KocoSa: Korean Context-aware Sarcasm Detection Dataset" accepted in COLING 2024.
The official implementation of Self-Play Fine-Tuning (SPIN)
🔊 Text-Prompted Generative Audio Model
Use API to call the music generation AI of suno.ai, and easily integrate it into agents like GPTs.
Robust recipes to align language models with human and AI preferences
[ICLR'24 spotlight] An open platform for training, serving, and evaluating large language model for tool learning.
The official implementation of Self-Play Preference Optimization (SPPO)
Official repo for the paper "Scaling Synthetic Data Creation with 1,000,000,000 Personas"
MatchTime: Towards Automatic Soccer Game Commentary Generation
Repository for “PlanRAG: A Plan-then-Retrieval Augmented Generation for Generative Large Language Models as Decision Makers”, NAACL24
A method to fix GPT-3 after deployment with user feedback, without re-training.
😎 A curated list of robotics libraries and software
[知识编辑] [ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.
[ACL 2024] A Prospector of Long-Dependency Data for Large Language Models
Level-Up is a Laravel package introducing gamification into your applications. Users earn experience points (XP) and levels through interactions, while also unlocking achievements. It promotes enga…
A fun tool for quickly browsing unsourced snippets on Wikipedia.
Obsidian Gamified PKM: Supercharge your knowledge management experience through gamification with this Obsidian plugin.
Fact-checking LLM outputs with self-ask
DSPy: The framework for programming—not prompting—foundation models