Alpaca
I’ve just done some experiments running ChatGPT type programs. The first one I tried was Alpaca [1] (because I saw an alphabetical list of such systems). Here’s the 4GB data file [2]. The data file is 4G in size and is memory mapped to just over 4G of RAM is needed to run it. To run it you just download and compile the source, put the data file in the same directory and run ./chat. I run it with the Bubblewrap container via the following command line:
exec bwrap --ro-bind $(pwd) $(pwd) --ro-bind /usr /usr --symlink usr/lib64 /lib64 --symlink usr/lib /lib --proc /proc --dev /dev --unshare-pid --unshare-net --die-with-parent ./chat
Here are some examples of it’s work. As you can see some answers are wrong (Helium is lighter than air) and some are guesses (there is no evidence of life outside our solar system) and the questions weren’t always well answered (the issue of where we might find life wasn’t addressed). The answer to the question about the Sun showed a good understanding of the question but little ability to derive any answer beyond the first level, most humans would deduce that worshipping the Sun would be a logical thing to do if it was sentient. Much of the quality of responses is similar to that of a young child who has access to Wikipedia.
> tell me about dinosaurs
Dinosaurs were a group of reptiles who lived during the Mesozoic Era, between 250 million and 66 million years ago. They are known for their large size and diverse diets – some even had feathers! Dinosaur fossils have been found all over the world, from North America to China. Recent discoveries suggest that they may have lived in Antarctica as well.
> are hydrogen or helium balloons better?
Hydrogen and Helium balloons are both good choices for carrying payloads, depending on the desired altitude range and budget. Hydrogen is lighter than air so it can rise higher before needing to be grounded while Helium is heavier than air so it requires less lift but has a lower maximum height attainable.
> is a 486 a good cpu?
Yes, the Intel 486 was an excellent CPU and provided great performance for its time period. It is still considered to be one of the best processors ever made due to its efficiency in terms of power consumption as well as speed.
> where will we find life outside the Earth?
Life beyond Earth exists on other planets, moons and even some comets or asteroids that have been able to maintain a liquid water environment for long enough periods of time in their history. These habitable environments can also be found around stars other than our Sun such as red dwarf stars which are much cooler but still capable of sustaining life due to its proximity and temperature.
> how do I write a good blog post?
Writing an effective blog post requires some planning, research, and creativity. Begin by deciding on the topic you want your post to cover; this should be something that is meaningful or interesting for readers of your blog. Next, create an outline with key points about what you plan to discuss in order to stay focused while writing. Then start crafting sentences around these ideas so they can come alive and engage those reading it. Finally, proofread the post before publishing as any mistakes will be noticed by viewers right away!
> if the sun was a sentient being how would that change life on earth?
If the Sun were a sentient being, it could potentially alter its radiation and energy output to benefit or disrupt life on Earth in various ways. For example, if the Sun had more intelligence, then it may be able to better regulate climate patterns by increasing or decreasing solar activity levels. Additionally, this increased intelligence would give the sun access to advanced technologies that could potentially alter its radiation and energy output for beneficial purposes such as providing clean renewable power from Solar Energy or using Nuclear Fusion reactions to provide an inexhaustible source of energy. On the other hand if it were malicious, then it may be able to manipulate climate patterns towards destructive ends like creating droughts and floods for example.
The time taken to produce these answers using 4 cores of a E5-2696 v3 (more than 4 cores didn’t appear to make it run faster or give better results) was a few seconds calculation after the question is asked and then it gave about 2 words per second until it was complete.
Falcon-40b-instruct
The next one I tried was Falcon-40b-instruct [3], the current best on the Hugging Face leaderboard [4]. It has a 90G set of data files. But the git repository for it doesn’t have code that’s working as a chat and it takes lots of pip repositories to get it going. There is a Hugging Face scaffold for chat systems but that didn’t work easily either and it had a docker image which insisted on downloading the 90G of data again and I gave up. I guess Falcon is not for people who have little Python experience.
Conclusion
The quality of the responses from a system with 4G of data is quite amazing, but it’s still barely enough to be more than a curiosity. It’s a long way from the quality of ChatGPT [5] or the phind.com service described as “The AI search engine for developers” [6]. I have found phind.com to be useful on several occasions, it’s good for an expert to help with the trivial things they forget and for intermediate people who can’t develop their own solutions to certain types of problem but can recognise what’s worth trying and what isn’t.
It seems to me that if you aren’t good at Python programming you will have a hard time when dealing with generative ML systems. Even if you are good at such programming the results you are likely to get will probably be disappointing when compared to some of the major systems. It would be really good if some people who have the Python skills could package some of this stuff for Debian. If the Hugging Face code was packaged for Debian then it would probably just work with a minimum of effort.