MiniGPT-4
mini-agi
| MiniGPT-4 | mini-agi | |
|---|---|---|
| 37 | 11 | |
| 24,899 | 2,759 | |
| 0.8% | - | |
| 9.1 | 8.8 | |
| 11 days ago | 11 months ago | |
| Python | Python | |
| BSD 3-clause "New" or "Revised" License | MIT License |
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.
MiniGPT-4
-
"Building Machines That Learn and Think Like People", 7 Years Later
I just think the tech has been out for so long it's not as big of a deal. Mini-Gpt4 has been out for 6 months! Of course the descriptions aren't exactly gpt-4 grade, but with mistral 7b being used as the language model instead of llama 7b, the reasoning ability will improve noticeably.
[1] https://github.com/Vision-CAIR/MiniGPT-4
- Minigpt4 Inference on CPU
-
Multimodal LLM for infographics images
Isn't there only two open multimodal LLMs, LLaVA and mini-gpt4?
-
Ai trained on photos
For LLM visual instruction, you can use LLaVA, LaVIN, or MiniGPT-4.
- CLIP and DeepDanbooru Alternatives For Prompt Generation [Relevant Self-Promotion]
-
Looking for a pre trained food recognition model
Please read the rules before posting. If you want a model for visual instruction, use LLaVA, LaVIN, or MiniGPT-4.
- Minigpt-4 (Vicuna 13B + images)
-
Upload a photo of your meal and get roasted by ChatGPT
So we use MiniGPT-4 for image parsing, and yep it does return a pretty detailed (albeit not always accurate) description of the photo. You can actually play around with it on Huggingface here.
We use MiniGPT-4 first to interpret the image and then pass the results onto GPT-4. Hopefully, once GPT-4 makes its multi-modal functionality available, we can do it all in one request.
-
Give some love to multi modal models trained on censored llama based models
But I would like to bring up that there are some multi models(llava, miniGPT-4) that are built based on censored llama based models like vicuna. I tried several multi modal models like llava, minigpt4 and blip2. Llava has very good captioning and question answering abilities and it is also much faster than the others(basically real time), though it has some hallucination issue.
mini-agi
- What AI OS projects are going on right now?
-
More experiments with MicroGPT, the GPT-based autonomous agent: 3D animation, boiling tea (more in the comments)
OP here, reporting back from testing the limits of what an autonomous agent powered by GPT-4 can accomplish... I hope it's of interest.
-
Source code review experiment with MicroGPT and GPT4
OP here. It's me again, the AI guy. This time I tried to get MicroGPT to do an interactive code review of WebGOAT .NET. If done on a per-function basis and with some guidance it produces a pretty reasonable result.
-
Use-case: Summoning cosmic horrors with GPT
I asked [MicroGPT](https://github.com/muellerberndt/micro-gpt) to summon The Great Old Ones. It did generate a playable audio file but so far, no cosmic horrors have shown up at my doorstep.
- GitHub - muellerberndt/micro-gpt: A minimal generic autonomous agent based on GPT-3.5 / GPT-4. Can analyze stock prices, perform network security tests, create art, and order pizza.
-
Making Snake and almost Space Invaders (MicroGPT + GPT-4)
This is another demo of MicroGPT with GPT-4. The snake game worked nicely, the Space Invaders game not so much :) Prompts:
-
Another nice screenshot of MicroGPT pwning a system
Clone the Github repo and follow the installation steps (set database to ChromaDB)
- [P] MicroGPT, a minimal autonomous agent (287 LoC) based on GPT3.5/4
-
MicroGPT, a mini-agent powered by GPT4, can analyze stocks, perform network security tests, and order Pizza. Link in the comments
MicroGPT is open-source & can be found here: https://github.com/muellerberndt/micro-gpt
- Here's my take on a minimal autonomous agent using GPT-4. Only 105 lines of code. It fails at ordering Pizza but is quite neat otherwise
What are some alternatives?
LLaVA - [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
AgentGPT - 🤖 Assemble, configure, and deploy autonomous AI Agents in your browser.
FastChat - An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
browsersnake - ChatGPT and I are pair programming on a browser implementation of the game snake
AutoGPT - 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.
stable-diffusion-webui-wd14-tagger - Labeling extension for Automatic1111's Web UI
BooruDatasetTagManager
bark - 🔊 Text-Prompted Generative Audio Model
Auto-GPT - An experimental open-source attempt to make GPT-4 fully autonomous. [Moved to: https://github.com/Significant-Gravitas/AutoGPT]
minigpt4-batch - Use miniGPT-4 batch to generate captions for a lot of images! You should be able to create the best captions you always wanted!
sd-webui-lobe-theme - 🅰️ Lobe theme - The modern theme for stable diffusion webui, exquisite interface design, highly customizable UI, and efficiency boosting features.
MiniGPT-4-discord-bot - A true multimodal LLaMA derivative -- on Discord!