open_flamingo
LLaMA-Adapter
open_flamingo | LLaMA-Adapter | |
---|---|---|
4 | 2 | |
3,493 | 5,535 | |
2.8% | 1.9% | |
6.8 | 8.1 | |
11 days ago | 2 months ago | |
Python | Python | |
MIT License | GNU General Public License v3.0 only |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
open_flamingo
-
Are there any multimodal AI models I can use to provide a paired text *and* image input, to then generate an expanded descriptive text output? [D]
Maybe the recent OpenFlamingo gives you better results (they have a demo on HF).
- [D] Multi modal for visual qna based on a given image. Need suggestions.
- Open Flamingo: An open-source framework for training large multimodal models
-
Announcing OpenFlamingo: An open-source framework for training vision-language models with in-context learning | LAION
Code here: https://github.com/mlfoundations/open_flamingo
LLaMA-Adapter
What are some alternatives?
transformers - 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
LoRA - Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
Emu - Emu Series: Generative Multimodal Models from BAAI
gpt4all - gpt4all: run open-source LLMs anywhere
pykale - Knowledge-Aware machine LEarning (KALE): accessible machine learning from multiple sources for interdisciplinary research, part of the 🔥PyTorch ecosystem. ⭐ Star to support our work!
Otter - 🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.
speechbrain - A PyTorch-based Speech Toolkit
bench-warmers - DigThatData's Public Brainstorming space
icl-ceil - [ICML 2023] Code for our paper “Compositional Exemplars for In-context Learning”.
chatgpt-telegram-bot - 🤖 A Telegram bot that integrates with OpenAI's official ChatGPT APIs to provide answers, written in Python
LocalAI - :robot: The free, Open Source OpenAI alternative. Self-hosted, community-driven and local-first. Drop-in replacement for OpenAI running on consumer-grade hardware. No GPU required. Runs gguf, transformers, diffusers and many more models architectures. It allows to generate Text, Audio, Video, Images. Also with voice cloning capabilities.