Explore projects
-
-
-
https://github.com/lm-sys/arena-hard-auto Arena-Hard-Auto: An automatic LLM benchmark.
Updated -
Examples in the MLX framework
Updated -
https://github.com/run-llama/llama_index LlamaIndex is a data framework for your LLM applications
Updated -
https://github.com/topoteretes/cognee Deterministic LLMs Outputs for AI Applications and AI Agents
Updated -
Hamilton helps data scientists and engineers define testable, modular, self-documenting dataflows, that encode lineage and metadata. Runs and scales everywhere python does.
Updated -
https://github.com/neelnanda-io/TransformerLens A library for mechanistic interpretability of GPT-style language models
Updated -
https://github.com/phidatahq/phidata Add memory, knowledge and tools to LLMs
Updated -
The Arcee client for executing domain-adpated language model routines
Updated -
https://github.com/Farama-Foundation/momaland Benchmarks for Multi-Objective Multi-Agent Decision Making
Updated -
https://github.com/mistralai/mistral-inference Official inference library for Mistral models
mistral.ai/
Updated -
https://github.com/jbloomAus/sae_vis This codebase was designed to replicate Anthropic's sparse autoencoder visualisations. The codebase provides 2 different views: a feature-centric view (which is like the one in the link,
Updated -
https://github.com/mistralai/cookbook The Mistral Cookbook features examples contributed by our community and partners. If you have cool examples showcasing Mistral models, feel free to share them by submitting a PR to this repo.
Updated -
Tools for merging pretrained large language models.
Updated