2

Faraday.dev

 1 year ago
source link: https://www.producthunt.com/posts/faraday-dev
Go to the source link to view the article. You can view the picture content, updated content and better typesetting reading experience. If the link is broken, please click the button below to view the snapshot at that time.
neoserver,ios ssh client
Ranked #10 for today

Faraday.dev

Run open-source LLMs on your computer

Discover the remarkable capabilities of open-source LLMs on your personal computer. Operate seamlessly without an internet connection and with effortless setup.
Hunter
Commenter
Commenter
Commenter
Commenter
Commenter
Commenter
Upvoter
Upvoter
Upvoter
Upvoter
Upvoter
Upvoter
Upvoter
Upvoter
Upvoter
Upvoter
Upvoter
Upvoter
Upvoter
Upvoter
Upvoter
Upvoter
Upvoter
Upvoter
Upvoter
Upvoter
Upvoter
Upvoter
Upvoter
Upvoter
Upvoter
Upvoter
Upvoter
Upvoter
Upvoter
Secureframe
Ad
Automated security compliance for your business in weeks
guest-user-avatar.png?auto=compress&codec=mozjpeg&cs=strip&auto=format&w=36&h=36&fit=crop
Sort by:

Introducing the ultimate solution for running open-source LLMs on your computer. No internet? No problem!

Just plug in and play with zero configuration hassle. Dive into language models directly on your device, supercharging your productivity and fueling your creative genius.

We currently support the following LLaMA-based models: - WizardLM 7B (Q5_0) - GPT4-x-Alpaca 13B (Q4_2) - GPT4-x-Alpaca 13B (Q4_0) - Vicuna 13B (Q4_2) - Vicuna 13B (Q4_3) - Koala 13B (Q4_3) - Open Assistant 13B (Q4_0) - PygmalionAI 7B (Q5_0) - PygmalionAI Metharme 7B (Q5_0) - Vicuna 7B (Q4_2) - Koala 7B (Q4_3) - Gpt-4-all 7B (Q4_0) - The Point 7B (Q4_0) - Gpt4-x-alpaca 30B (Q5_0)

This is super cool, congrats on the launch!! Seems super easy to launch up your own AI, I'll definitely give it a shot. Is there a plan for a Linux version? :)
What are the requirements for running LLMs on your computer. I have read llama.ccp needs 64gb ram++ and latest M2 Ultra cpus etc. 😅 And then it runs, but a bit slow. With gpt3 like capabilities.

Looks great! From a UX perspective: I would have added more info on the landing page what your tool is specifically capable of and what it can't be used for. Maybe just a FAQ section is enough to clear up details and reassure users.

Not all users will have the time or ability to watch a video (internet restrictions, office networks, on the road with slower Mobile/Wifi connections), and you still have enough vertical space available on your landing page to introduce a icon grid, a FAQ section or some other explainer sections to drive home the value of your product.

For starters, the information you provided here on ProductHunt for example.

I also don't see any docs, although you do link to a discord. Again, a video might not be enough to explain this. A step by step can reinforce/market the simplicity of your app and how it works on the different operating Systems.

Other than that, I think its a great idea to accumulate open source LLMs under one roof! Its just that a video alone is not a great conversion tool for a website.


About Joyk


Aggregate valuable and interesting links.
Joyk means Joy of geeK