Stars
Library for fast text representation and classification.
A one-stop data processing system to make data higher-quality, juicier, and more digestible for (multimodal) LLMs! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷为大模型提供更高质量、更丰富、更易”消化“的数据!
Data and tools for generating and inspecting OLMo pre-training data.
Modeling, training, eval, and inference code for OLMo
OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.
MetaRF: Differentiable Random Forest for Reaction Yield Prediction with a Few Trails
Open-Sora: Democratizing Efficient Video Production for All
Implementation of Alpha Fold 3 from the paper: "Accurate structure prediction of biomolecular interactions with AlphaFold3" in PyTorch
PyAutoFEP: an automated FEP workflow for GROMACS integrating enhanced sampling methods
VideoSys: An easy and efficient system for video generation
MiniSora: A community aims to explore the implementation path and future development direction of Sora.
Resources and Implementations of Generative Adversarial Nets: GAN, DCGAN, WGAN, CGAN, InfoGAN
Train transformer language models with reinforcement learning.
Collection of links, tutorials and best practices of how to collect the data and build end-to-end RLHF system to finetune Generative AI models
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Reference implementation for DPO (Direct Preference Optimization)
For language generative model training and RLHF fine-tuning practise
Alphafold2 no docker jax jaxlib configuration
A Tool to process and visualize the results of molecular dynamics simulations(GROMACS).
[Unmaintained, see README] An ecosystem of Rust libraries for working with large language models
This repo is based on clauswilke/PeptideBuilder and Lun4m/PeptideBuilder.
⏩ Continue is the leading open-source AI code assistant. You can connect any models and any context to build custom autocomplete and chat experiences inside VS Code and JetBrains