phasellm
LLM framework
A framework for managing and testing large language models to evaluate their performance and optimize user experiences.
Large language model evaluation and workflow framework from Phase AI.
451 stars
9 watching
25 forks
Language: Python
last commit: 7 months ago
Linked from 1 awesome list
aigptllmopenaipython
Related projects:
Repository | Description | Stars |
---|---|---|
| A high-performance LLM written in Python/Jax for training and inference on Google Cloud TPUs and GPUs. | 1,557 |
| Provides a comprehensive framework for evaluating Large Language Model (LLM) applications and pipelines with customizable metrics | 455 |
| A tool for evaluating the performance of large language model APIs | 678 |
| A framework that enables large language models to process and understand multimodal inputs from various sources such as images and speech. | 308 |
| A lightweight framework for building agent-based applications using LLMs and transformer architectures | 1,924 |
| A large-scale language model for scientific domain training on redpajama arXiv split | 125 |
| A framework for training GPT4-style language models with multimodal inputs using large datasets and pre-trained models | 231 |
| Enables users to engage with multiple large language models simultaneously and access their APIs | 256 |
| An open-source implementation of a vision-language instructed large language model | 513 |
| An evaluation suite and dynamic data release platform for large language models | 230 |
| An open-source toolkit for building and evaluating large language models | 267 |
| A security toolkit designed to protect interactions with large language models from various threats and vulnerabilities. | 1,296 |
| An effort to develop and compare large language models beyond OpenGPT | 105 |
| A flexible RL training framework designed for large language models | 427 |
| A framework and benchmark for training and evaluating multi-modal large language models, enabling the development of AI agents capable of seamless interaction between humans and machines. | 305 |