Starred repositories
Intelligent Mixture-of-Models Router for Efficient Heterogeneous LLMs Inference
SSE (Stable Static Embedding): Unlocking the Potential of Static Embeddings, A Dynamic Tanh Normalization Approach without Speed Penalty
An extensive and commented list of resources on Late-Interaction Multivector Retrieval.
Personal-Model First Self Evolving AI Agent 🐘
🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models
Official Python library for the TeraflopAI API
Robust and fast topic models with sentence-transformers.
Give your agents the power of the Hugging Face ecosystem
mishig25 / hf-autoresearch
Forked from karpathy/autoresearchAI agents running research on Hugging Face infra
Mount Hugging Face Buckets and repos as local filesystems. No download, no copy, no waiting.
Hundreds of models & providers. One command to find what runs on your hardware.
Fine-tune SPLADE sparse embedding models for your product catalog. CLI, web dashboard, and Python API.
A missing piece of the Python multitask (both threads and processes) API: An extension that supports stateful worker pools & size-aware iterators.
A lightweight inference engine supporting speculative speculative decoding (SSD).
Build compute kernels and load them from the Hub.
Implementation for Revela: Dense Retriever Learning via Language Modeling - ICLR 2026 Oral
Text and code embeddings research from CodeFuse: C2LLM, D2LLM, E2LLM, F2LLM, ML-Embed
Fast BM25 search engine with category theory abstractions
Mutlimodal reranker training and benchmarks
Nearly Inference Free Embeddings: make your RAG queries 500x faster