Train Models Contrastively in Pytorch
- contrastive-learning
- deep-learning
- embeddings
- pytorch
142,273 visible repositories in the index
1–10 of 10 · Most stars
Train Models Contrastively in Pytorch
Rust-powered code intelligence CLI for AI coding agents. Builds call graphs and hybrid semantic search indexes (Dense + Sparse + RRF + Reranker) across 7 languages. Ships as native MCP tools for Claude Code and Codex CLI.
[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization
[CVPR 2024] MovieChat: From Dense Token to Sparse Memory for Long Video Understanding
Official Codebase for "Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights" (ICML 2026 Spotlight)
HyDE: Precise Zero-Shot Dense Retrieval without Relevance Labels
Train and Infer Powerful Sentence Embeddings with AnglE | 🔥 SOTA on STS and MTEB Leaderboard
Long Horizon Terminal Benchmark with Dense Reward Grading
AI Vim/Neovim code generation plugin (OpenAI, ChatGPT, and more)
Calibrated internal-state modulation, readout, and neural observability for local dense language models.