A Bach music generator with Artificial Intelligence. This model is made by a VQ-VAE + Transformer (decoder-only). Sequences of midi 1 quarter length are compressed into 16 codebooks via VQ-VAE and a transformer learns how to generate the codebooks sequence to obtain a midi score.
High-Performance Transformers for Table Structure Recognition Need Early Convolutions
Code for the paper "Aligning LLM Agents by Learning Latent Preference from User Edits".
Google QUEST Q&A Labeling Kaggle Competition 6th Place Solution
Framework to evaluate Trajectory Classification Algorithms
A meta-framework for self-improving LLMs with transparent reasoning
Automate web research way beyond the first page of search results; curate knowledge bases to chat with.
🤗 Push your spaCy pipelines to the Hugging Face Hub
Generate degraded speech datasets for noise-robust ASR benchmarking
Universal vector search wrapper for Postgres, MySQL, SQLite (pgvector, Vector Store, sqlite‑vss).
Moondream is a lightweight multimodal large language model
NVDiffrast based implementation of Latent-Paint
共 9101 条 · 第 389 / 456 页