- United Kingdom
- http://www.janisklaise.com
LLMs
🍰 PromptLayer - Maintain a log of your prompts and OpenAI API requests. Track, debug, and replay old completions.
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.
A method to fix GPT-3 after deployment with user feedback, without re-training.
🦜🔗 Build context-aware reasoning applications
Code for the paper "ViperGPT: Visual Inference via Python Execution for Reasoning"
A language for constraint-guided and efficient LLM programming.
The simplest, fastest repository for training/finetuning medium-sized GPTs.
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…
📋 A list of open LLMs available for commercial use.
Seamlessly integrate LLMs into scikit-learn.
A high-throughput and memory-efficient inference and serving engine for LLMs
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Python package for easily interfacing with chat apps, with robust features and minimal code complexity.
🤖 A PyTorch library of curated Transformer models and their composable components
Accessible large language models via k-bit quantization for PyTorch.
Large Language Model Text Generation Inference
Running large language models on a single GPU for throughput-oriented scenarios.
SkyPilot: Run AI and batch jobs on any infra (Kubernetes or 14+ clouds). Get unified execution, cost savings, and high GPU availability via a simple interface.
Universal LLM Deployment Engine with ML Compilation
Fast inference engine for Transformer models
Adding guardrails to large language models.
Ungreedy subword tokenizer and vocabulary trainer for Python, Go & Javascript