#
Lists (3)
Starred repositories
ArcticTraining is a framework designed to simplify and accelerate the post-training process for large language models (LLMs)
Implementation of the Cypher language for searching NetworkX graphs
Python toolkit for building graph-enhanced GenAI applications
Fast and extensible multi-platform HTTP/1-2-3 web server with automatic HTTPS
The simplest, fastest repository for training/finetuning small-sized VLMs.
An on-premises, OCR-free unstructured data extraction, markdown conversion and benchmarking toolkit. (https://idp-leaderboard.org/)
NewBornRustacean / burn
Forked from tracel-ai/burnBurn is a new comprehensive dynamic Deep Learning Framework built using Rust with extreme flexibility, compute efficiency and portability as its primary goals.
NewBornRustacean / ndarray
Forked from rust-ndarray/ndarrayndarray: an N-dimensional array with array views, multidimensional slicing, and efficient operations
zhou-yuxin / optimized-faiss
Forked from facebookresearch/faissA library for efficient similarity search and clustering of dense vectors.
💎 Amber the programming language compiled to Bash
🔩 The open-source serverless platform. Easily deploy & scale AI agents, complex workloads, and backends — all on a frictionless platform that runs anywhere.
Kafka Streams + Java + gRPC + TensorFlow Serving => Stream Processing combined with RPC / Request-Response
A Dead Simple BERT API for Python and Java (https://github.com/google-research/bert)
Claude Code as one-shot MCP server to have an agent in your agent.
Reverse Engineering Claude Code with LLMs: A Deep Dive into the Minified 4.6MB cli.mjs
mxbai-rerank-large-v2 & mxbai-rerank-base-v2 with infinity inference with this classifier proxy translating classifier into rerank endpoint
A general fine-tuning kit geared toward diffusion models.
Scalable and memory-optimized training of diffusion models
Video-based AI memory library. Store millions of text chunks in MP4 files with lightning-fast semantic search. No database needed.
High-Performance Engine for Multi-Vector Search
This algorithm implements Karcher mean-based weight fusion, which geometrically combines model parameters on the unit sphere while preserving their directional relationships and global scaling.
Neon: Serverless Postgres. We separated storage and compute to offer autoscaling, code-like database branching, and scale to zero.
Model implementation for the contextual embeddings project
memory-bank-mcp-server