Stars
Transplants vocabulary between language models, enabling the creation of draft models for speculative decoding WITHOUT retraining.
Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
Official repository for our NeurIPS 2023 paper "Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense" (https://arxiv.org/abs/2303.13408).
GUI for ChatGPT API and many LLMs. Supports agents, file-based QA, GPT finetuning and query with web search. All with a neat UI.
BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)
High-performance In-browser LLM Inference Engine