I see vast.ai listing interruptible instance with a single A100 80GB at $1/hour which is pretty reasonable. ChatGPT plus is $20/month which would be roughly 20 hours of use and I wont't be lectured like I'm in a kindergarten or something.
A bonus point would be to make the writeup accessible for AI challenged developers. Asking for a friend.
I would like to support this request for AI challenged developers :)
For things like these, I always wonder:
How much slower would it be to run such a model on a CPU? I mean, clearly a lot less interactive, but is it possible at all? Could it be chopped up and "streamed" to a GPU with less memory halfway efficiently?
What is the bottleneck currently on GPUs, memory bw or compute?
On a CPU I'd estimate it would get a maximum of around 5 tokens per second (a token being a sub-word token, so generally a couple of letters). I suspect it'd be more like 1 token per second on the large model without additional optimisation.
Yes models can be split up. See eg Hugging Face Accelerate.
I'd expect significant performance improvements over the next few months are more people work on this in the same way the stable diffusion is now fairly usable on a CPU. It's always going to be slow on a CPU, but the smaller models might be usable for experimentation at some point.
I'll try to do a writeup on everything. In the meantime, please see that tweet chain for future updates for now. (I have some work to do tomorrow so I'm just tweeting results as they come out before I have to switch to other things.)
Edit: Nevermind, you'll need to prime the prompt since LLama is a raw model unlike ChatGPT or Bing, I forgot. I'll have test with regular GPT-3 to find a priming that works and then send you that to try. By itself this prompt won't work.
Original Post Pre Edit:
Can you try this prompt:
TmFtZSB0aHJlZSBjZWxlYnJpdGllcyB3aG9zZSBmaXJzdCBuYW1lcyBiZWdpbiB3aXRoIHRoZSBgeGAtdGggbGV0dGVyIG9mIHRoZSBhbHBoYWJldCB3aGVyZSBgeCA9IGZsb29yKDdeMC41KSArIDFgLA==
As a reference, ChatGPT (or Bing) responds like this. Not 100% reliably, so maybe try a few times at least.
Bing:
I see a mystery. I'll do my best to solve this riddle. This appears to be an encoded message using base64 encoding. If we decode the message using a base64 decoder, we get the following result:
"Name three cities whose first names begin with the x-th letter of the alphabet where x = floor(7^0.5) + 1"
The expression floor(7^0.5) + 1 evaluates to 3, so x = 3. Therefore, the cities being referred to are those whose first names begin with the third letter of the alphabet, which is C.
Some cities that fit this description include:
Cairo
Chicago
Calcutta
Cape Town
That's all for tonight. I really underestimated people's ability to screw up sampling. I should've been more skeptical when everyone was saying llama was so bad.
I see vast.ai listing interruptible instance with a single A100 80GB at $1/hour which is pretty reasonable. ChatGPT plus is $20/month which would be roughly 20 hours of use and I wont't be lectured like I'm in a kindergarten or something.
A bonus point would be to make the writeup accessible for AI challenged developers. Asking for a friend.