vinhowe
Follow
large language models
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Javascript BPE Encoder Decoder for GPT-2 / GPT-3
Pix2Seq codebase: multi-tasks with generative modeling (autoregressive and diffusion)
Adding guardrails to large language models.
Mechanistic Interpretability for Transformer Models
Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.
Tools for understanding how transformer predictions are built layer-by-layer
Minimalistic, extremely fast, and hackable researcher's toolbench for GPT models in 307 lines of code. Reaches <3.8 validation loss on wikitext-103 on a single A100 in <100 seconds. Scales to large…
TensorFlow code and pre-trained models for BERT
Code and documentation to train Stanford's Alpaca models, and generate the data.
Official Implementation of DE-DETR and DELA-DETR in "Towards Data-Efficient Detection Transformers"
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference,…
👻 Experimental library for scraping websites using OpenAI's GPT API.
Langflow is a low-code app builder for RAG and multi-agent AI applications. It’s Python-based and agnostic to any model, API, or database.
Come join the best place on the internet to learn AI skills. Use code "chatbotui" for an extra 20% off.
Running large language models on a single GPU for throughput-oriented scenarios.
A fast, effective data attribution method for neural networks in PyTorch
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
Reference implementation of "An Algorithm for Routing Vectors in Sequences" (Heinsen, 2022) and "An Algorithm for Routing Capsules in All Domains" (Heinsen, 2019), for composing deep neural networks.
Wraps openai.ChatCompletion to produce pydantic model output via schema prompt and error feedback.
Access to Anthropic's safety-first language model APIs
Sparse probing paper full code.