Find better generation parameters for your LLM
APACHE-2.0 License
Published by Praful932 5 months ago
Chain-of-Hindsight, A Scalable RLHF Method
Home of StarCoder2!
My Digital Palace - A Personal Journal for Reflection - A place to store all my thoughts
Transformer with Untied Positional Encoding (TUPE). Code of paper "Rethinking Positional Encoding...
Transformer models implementation for training from scratch.
Unsupervised Language Modeling at scale for robust sentiment classification
LangChain chat model abstractions for dynamic failover, load balancing, chaos engineering, and more!
Embed arbitrary modalities (images, audio, documents, etc) into large language models.
This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critiqu...
LongLLaMA is a large language model capable of handling long contexts. It is based on OpenLLaMA a...
Ongoing research training transformer models at scale
Hybrid Discriminative-Generative Training via Contrastive Learning
Generate textbook-quality synthetic LLM pretraining data
Home of StarCoder: fine-tuning & inference!