Scaling Coding-Agent RL to 32x H100s. **Achieving 160% improvement** on Stanford's TerminalBench

Textbook on reinforcement learning from human feedback

State of the Art Natural Language Processing

Train transformer language models with reinforcement learning.

Use smol agents to do research and then update csv coumns with its findings.

Large Language Model Text Generation Inference

Open source codebase powering the HuggingChat app

The official evaluation suite and dynamic data release for MixEval.

🧡 Hacker News summaries

Go ahead and axolotl questions

LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath

Snowflake LLM-based text to SQL and document retrieval in Streamlit

The landscape of biomedical research

Deliver safe & effective NLP models

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Port of Facebook's LLaMA model in C/C++

Multi-user server for Jupyter notebooks

Model API for GALACTICA

Various gRPC benchmarks