Empowering RAG with a memory-based data interface for all-purpose applications!

Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

ExtractThinker is a Document Intelligence library for LLMs, offering ORM-style interaction for flexible and powerful document workflows.

Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/

From zero to hero CUDA for accelerating maths and machine learning on GPU.

Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.

Recipes to train reward model for RLHF.

Arena-Hard-Auto: An automatic LLM benchmark.

Efficient LLM Inference Acceleration using Prompting

深度学习500问，以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述，以帮助自己及有需要的读者。 全书分为18个章节，50余万字。由于水平有限，书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作，联系scutjy2015@163.com 版权所有，违权必究 Tan 2018.06

Official code for "MAmmoTH2: Scaling Instructions from the Web"

🐋 An unofficial implementation of Self-Alignment with Instruction Backtranslation.

Llama3-Chinese是以Meta-Llama-3-8B为底座，使用 DORA + LORA+ 的训练方法，在50w高质量中文多轮SFT数据 + 10w英文多轮SFT数据 + 2000单轮自我认知数据训练而来的大模型。

Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.

Low-code framework for building custom LLMs, neural networks, and other AI models

🐳 Aurora is a [Chinese Version] MoE model. Aurora is a further work based on Mixtral-8x7B, which activates the chat capability of the model's Chinese open domain.

Best practices for distilling large language models.

The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text

LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath

Database for AI. Store Vectors, Images, Texts, Videos, etc. Use with LLMs/LangChain. Store, query, version, & visualize any AI data. Stream data in real-time to PyTorch/TensorFlow. https://activelo…

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！

The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, and more.

Aligning pretrained language models with instruction data generated by themselves.

Argilla is a collaboration tool for AI engineers and domain experts to build high-quality datasets

Machine Learning Engineering Open Book

Official code for "Large Language Models Are Reasoning Teachers", ACL 2023

self-adaptive in-context learning

Retrieval Augmented Generation (RAG) chatbot powered by Weaviate

Lightweight chat AI platform featuring custom knowledge, open-source LLMs, prompt-engineering, retrieval analysis. Highly customizable. For Retrieval-Centric & Retrieval-Augmented Generation.