KhoomeiK / LlamaGymLinks
Fine-tune LLM agents with online reinforcement learning
☆1,242Updated last year
Alternatives and similar repositories for LlamaGym
Users that are interested in LlamaGym are comparing it to the libraries listed below
Sorting:
- Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI☆1,399Updated last year
- [ICML 2024] Official repository for "Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models"☆798Updated last year
- LLM Analytics☆695Updated last year
- Code and data for "Lumos: Learning Agents with Unified Data, Modular Design, and Open-Source LLMs"☆471Updated last year
- DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models. 🤖💤☆1,077Updated 9 months ago
- Official codebase for the paper "Beyond A* Better Planning with Transformers via Search Dynamics Bootstrapping".☆375Updated last year
- A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and full…☆624Updated 7 months ago
- Agents Capable of Self-Editing Their Prompts / Python Code☆775Updated last year
- ☆1,035Updated 10 months ago
- Code repo for "WebArena: A Realistic Web Environment for Building Autonomous Agents"☆1,218Updated last month
- Code for Quiet-STaR☆741Updated last year
- Finetune llama2-70b and codellama on MacBook Air without quantization☆450Updated last year
- Visualize the intermediate output of Mistral 7B☆378Updated 9 months ago
- An LLM-based autonomous agent controlling real-world applications via RESTful APIs☆1,387Updated last year
- Vision utilities for web interaction agents 👀☆1,740Updated 11 months ago
- Easily train AlphaZero-like agents on any environment you want!☆431Updated last year
- ☆748Updated last year
- A lightweight library for generating synthetic instruction tuning datasets for your data without GPT.☆801Updated 4 months ago
- The official implementation of Self-Play Fine-Tuning (SPIN)☆1,213Updated last year
- An LLM-powered advanced RAG pipeline built from scratch☆854Updated last year
- Neum AI is a best-in-class framework to manage the creation and synchronization of vector embeddings at large scale.☆864Updated last year
- Code behind Arxiv Papers☆535Updated last year
- xLAM: A Family of Large Action Models to Empower AI Agent Systems☆578Updated 2 months ago
- Inference code for Persimmon-8B☆412Updated 2 years ago
- A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta.☆2,951Updated last week
- ☆415Updated last year
- Recipes to scale inference-time compute of open models☆1,117Updated 5 months ago
- Implementation of Google's SELF-DISCOVER☆299Updated last year
- A library for generative social simulation☆1,069Updated last week
- Benchmarking long-form factuality in large language models. Original code for our paper "Long-form factuality in large language models".☆651Updated 3 months ago