RAFT, or Retrieval-Augmented Fine-Tuning, is a method comprising of a fine-tuning and a RAG-based retrieval phase. It is particularly suited for the creation of agents that realistically emulate a specific human target.
DantinoX: A modular, memory-efficient Transformer implementation in JAX/Flax NNX. Includes Sparse MoE, GQA, Sliding Window Attention, Gradient Accumulation and Checkpointing
