Starling-7B

Enhancing the usability and safety of LLM

CommonProductchattingLanguage ModelReinforcement Learning

Visit

Starling-7B is an open-weights large language model (LLM) trained using Reinforcement Learning from AI Feedback (RLAIF). It was trained effectively leveraging our new GPT-4 labeled ranking dataset, Nectar, and a novel reward training and policy optimization process. Starling-7B achieved a score of 8.09 on MT Bench, with GPT-4 as the judge, surpassing all existing models except OpenAI's GPT-4 and GPT-4 Turbo. We have released the ranked dataset Nectar, the reward model Starling-RM-7B-alpha, the language model Starling-LM-7B-alpha on HuggingFace, and an online demo on LMSYS Chatbot Arena. Stay tuned for the upcoming release of our code and paper, which will provide more details about the entire process.

Product Finder

Product Submit

AI Models Finder

MCP Servers

MCP Client

MCP Inspector

Case Tutorials

Latest AI News

AI Daily Brief

Starling-7B

Starling-7B Visit Over Time

Starling-7B Visit Trend

Starling-7B Visit Geography

Starling-7B Traffic Sources

Starling-7B Alternatives

Language Learning Games — AI text adventure games for language learning

d1 — Improving the reasoning capabilities of diffusion large language models using reinforcement learning.

mwp_ReFT — A deep reinforcement learning-based model fine-tuning framework

VLM-R1 — VLM-R1 is a stable and versatile reinforcement learning-enhanced visual-language model focused on visual understanding tasks.

Search-R1 — A highly efficient reinforcement learning framework for training language models that perform reasoning and call search engines.

Language Atlas — Free language learning

LangMob — Anytime, anywhere language learning with an AI chatbot language learning app

DIAMOND — A reinforcement learning agent trained in a diffusion world model

DeepSeek-R1-Distill-Llama-70B — DeepSeek-R1-Distill-Llama-70B is a large language model optimized using reinforcement learning, focusing on reasoning and conversational capabilities.

Language REACTOR — A powerful language learning toolkit

DeepScaleR-1.5B-Preview — A large language model optimized by reinforcement learning, focusing on enhancing mathematical problem-solving skills.

Light-R1-14B-DS — An open-source 14B-parameter mathematical model, trained using reinforcement learning, with excellent performance.

SWE-RL — Enhancing the reasoning capabilities of large language models in open-source software evolution through reinforcement learning.

SERL — SERL is an efficient robot reinforcement learning software suite

DiffusionRL — Large-scale Reinforcement Learning for Diffusion Models

Fin-R1 — A large language model for financial reasoning driven by reinforcement learning.

Unitree RL GYM — Unitree robot platform for reinforcement learning

Trustworthy Language Model (TLM) Playground — Try Cleanlab's Trustworthy Language Model (TLM) in your browser

agibot_x1_train — Modular humanoid robot for reinforcement learning training

RLVR-GSM-MATH-IF-Mixed-Constraints — A dataset of math problems for reinforcement learning validation.

LMSYS Chatbot Arena — An online chatbot arena where the performance of different language models is compared.

JaxMARL — JaxMARL - A multi-agent reinforcement learning library

Starling-7B — Enhancing the usability and safety of LLM

R1-Omni — R1-Omni is a full-modality emotion recognition model incorporating reinforcement learning, focusing on improving the interpretability of multimodal emotion recognition.

Tülu 3 405B — Tülu 3 405B is a large-scale open-source language model enhanced through reinforcement learning.

DigiRL — Train outdoor device control agents using autonomous reinforcement learning

Kimi k1.5 — Kimi k1.5 is a multimodal language model enhanced by reinforcement learning, focused on improving reasoning and logical abilities.

Linguisticat — The purrfect language learning tool.

Parrot — Multi-target Reinforcement Learning Framework for Text-to-Image Generation

HuatuoGPT-o1 — A large language model for complex reasoning in the medical field