Open source replication of Anthropic's Crosscoders for Model Diffing

The code for creating the iGSM datasets in papers "Physics of Language Models Part 2.1, Grade-School Math and the Hidden Reasoning Process" (arxiv 2407.20311) and "Physics of Language Models Part 2…

A curated list of LLM Interpretability related material - Tutorial, Library, Survey, Paper, Blog, etc..

A curated list of Large Language Model (LLM) Interpretability resources.

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

RLHF implementation details of OAI's 2019 codebase

Robust recipes to align language models with human and AI preferences

Train transformer language models with reinforcement learning.

A course on aligning smol models.

A curated list of reinforcement learning with human feedback resources (continually updated)

verl: Volcano Engine Reinforcement Learning for LLMs

Simple RL training for reasoning

Scalable RL solution for advanced reasoning of language models

Training Large Language Model to Reason in a Continuous Latent Space

强化学习中文教程（蘑菇书🍄），在线阅读地址：https://datawhalechina.github.io/easy-rl/

Building Open LLM Web Agents with Self-Evolving Online Curriculum RL

LLMs as Copilots for Theorem Proving in Lean

🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

Calculate perplexity on a text with pre-trained language models. Support MLM (eg. DeBERTa), recurrent LM (eg. GPT3), and encoder-decoder LM (eg. Flan-T5).

Code for CRATE (Coding RAte reduction TransformEr).