meta-llama / PurpleLlamaLinks
Set of tools to assess and improve LLM security.
☆3,464Updated this week
Alternatives and similar repositories for PurpleLlama
Users that are interested in PurpleLlama are comparing it to the libraries listed below
Sorting:
- PyTorch native post-training library☆5,257Updated this week
- A PyTorch native platform for training generative AI models☆3,912Updated this week
- Agentic components of the Llama Stack APIs☆4,252Updated last month
- ☆3,692Updated last month
- Tools for merging pretrained large language models.☆5,809Updated this week
- Go ahead and axolotl questions☆9,553Updated this week
- ☆2,527Updated last year
- The official Meta Llama 3 GitHub site☆28,776Updated 4 months ago
- The official PyTorch implementation of Google's Gemma models☆5,474Updated 2 weeks ago
- Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.☆2,400Updated last week
- lightweight, standalone C++ inference engine for Google's Gemma models.☆6,466Updated this week
- AllenAI's post-training codebase☆3,007Updated this week
- Cohere Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications.☆3,054Updated this week
- ☆4,083Updated last year
- Robust recipes to align language models with human and AI preferences☆5,214Updated last month
- Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We als…☆17,454Updated this week
- Training LLMs with QLoRA + FSDP☆1,484Updated 7 months ago
- The Python Risk Identification Tool for generative AI (PyRIT) is an open source framework built to empower security professionals and eng…☆2,587Updated this week
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆2,752Updated this week
- Utilities intended for use with Llama models.☆7,068Updated last week
- SWE-bench [Multimodal]: Can Language Models Resolve Real-world Github Issues?☆3,069Updated last week
- Reaching LLaMA2 Performance with 0.1M Dollars☆982Updated 10 months ago
- ☆2,956Updated 9 months ago
- Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-…☆3,492Updated 3 weeks ago
- Doing simple retrieval from LLM models at various context lengths to measure accuracy☆1,886Updated 9 months ago
- Minimalistic large language model 3D-parallelism training☆1,914Updated this week
- Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs☆3,010Updated 3 weeks ago
- CoreNet: A library for training deep neural networks☆7,015Updated last month
- Modeling, training, eval, and inference code for OLMo☆5,666Updated this week
- A unified evaluation framework for large language models☆2,630Updated 2 weeks ago