adept-inference
GPT-V-on-Web
adept-inference | GPT-V-on-Web | |
---|---|---|
3 | 2 | |
411 | 155 | |
0.2% | - | |
4.9 | 6.8 | |
9 months ago | 7 months ago | |
Python | Python | |
Apache License 2.0 | GNU Affero General Public License v3.0 |
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.
adept-inference
- Adept
-
Using GPT-4 Vision with Vimium to browse the web
Ah, very similar to Adept’s[1] concept? Though, their product seems not yet ready.
[1] https://www.adept.ai/
-
Releasing Persimmon-8B
https://github.com/persimmon-ai-labs/adept-inference/issues/...
It’s funny you say production, because all of the errors I ran into suggest the container is expecting your production architecture.
My advice is stream first then make synchronous convenience wrappers on top of that. Also, lean on community standards for PoC. I’m guess your investors are interested in making this scale as cheaply as possible, but that is probably the least important feature for people evaluating your model’s quality locally.
GPT-V-on-Web
-
Using GPT-4 Vision with Vimium to browse the web
Omg I also just released something pretty similar earlier today https://github.com/Jiayi-Pan/GPT-V-on-Web. But it received little attention.
- GPT-4 Vision X Vimium as Autonomous Web Agent
What are some alternatives?
OpenAdapt - AI-First Process Automation with Large ([Language (LLMs) / Action (LAMs) / Multimodal (LMMs)] / Visual Language (VLMs)) Models
vimGPT - Browse the web with GPT-4V and Vimium
CogVLM - a state-of-the-art-level open visual language model | 多模态预训练模型
LLaVA - [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
vim-agent