24 Comentários

1. From $1499 buy comma.ai/shop/comma-three | github.com/geohot/tinygrad/blob/llama/examples/llama.py | https://github.com/geohot/tinygrad/tree/llama | tiny corp has a website tinygrad.org | Check out and star github.com/geohot/tinygrad | Support George by subscribing twitch.tv/subs/georgehotz | Follow George on instagram.com/georgehotz & twitch.tv/georgehotz & twitter.com/comma_ai to be up to date | Read George's geohot.github.io/blog/ | Programming archive🡿 youtube.com/playlist?list=PLzFUMGbVxlQs5s-LNAyKgcq5SL28ZLLKC
   
   Chapters:
   
   00:00:00 muted intro
   
   00:00:50 missing the rant about bad mood
   
   00:01:35 not family friendly content
   
   00:01:55 hardware to run tinygrad
   
   00:02:10 don't mess with george
   
   00:02:35 what we did yesterday
   
   00:05:00 where are we wasting time, not limited by gpu
   
   00:06:20 python snakeprof
   
   00:10:30 tinygrad discord llama channel, hacker news blow up
   
   00:10:45 llama weights on torrent
   
   00:11:20 does it run on nvidia 3090, ram
   
   00:13:30 open assistant product, prompt engineering
   
   00:21:10 no limits, don't believe in ai safety
   
   00:21:40 no guns, ai stupid
   
   00:23:55 what you need to torrent for weights
   
   00:27:25 torch.triu
   
   00:32:25 nice pytorch error messages
   
   00:36:45 russian mode
   
   00:38:00 python bottleneck
   
   00:41:50 twitch chat not paying attention
   
   00:42:50 pull request to facebook
   
   00:43:50 hacker news, gotham chess plays chatgpt
   
   00:45:30 chatbot loop
   
   00:47:00 asking questions, bad enter
   
   00:50:20 no ai filter
   
   00:51:40 interesting output
   
   00:53:50 sentencepieceprocessor decode_piece
   
   00:58:00 removing extra enter
   
   01:00:50 decode token to token, this is the problem
   
   01:02:50 we learned how to take it out of russian mode
   
   01:03:50 need demo answers, it's called llama chat
   
   01:06:30 be verbose in your answers
   
   01:08:00 call back humor answer
   
   01:08:50 pastebin improved pre prompts
   
   01:17:00 not Gale, your name is Brian, cookies
   
   01:18:00 what is your prompt
   
   01:18:35 arbitrary python
   
   01:22:45 impressive large language models
   
   01:30:50 running on M1 Max
   
   01:36:30 llama link
   
   01:37:30 Brian running wild
   
   01:39:00 real talk about ai safety
   
   01:40:20 chat llama open source, running in web browser
   
   01:42:20 funny response
   
   01:43:45 connecting to the internet
   
   01:45:00 model too small, too many tokens
   
   01:47:00 darth vader, used car salesman name
   
   01:50:30 Lana_Lux raiding stream, explaining to new people
   
   01:51:15 what makes chatgpt good
   
   01:52:00 fun answer
   
   01:53:00 Gary only has 7B weights
   
   01:54:10 chatml, need smarter model
   
   02:00:00 what we should do?
   
   02:01:00 bad rapper
   
   02:03:20 stacy
   
   02:07:15 limits of 7B weights
   
   02:08:50 good answer
   
   02:09:25 assuming gender
   
   02:11:25 searching snapchat mentee.dreams
   
   02:12:12 replica terrible, asking more questions, rap
   
   02:17:10 13B weights smart stacy, vram requirements
   
   02:19:30 running on cpu, took a day to write this in tinygrad
   
   02:21:55 comma build the best self driving car, tinygrad taking over the world
   
   02:22:40 removing code, repetition penalty
   
   02:30:10 testing stacy
   
   02:36:10 sp_model.decode_pieces, bos_id
   
   02:43:20 fun answer, need to make large work
   
   02:50:10 reading the LLaMA paper
   
   02:52:10 anyone running this on his mac?, code pushed
   
   02:53:45 macbook air m2
   
   02:59:15 pytorch split file
   
   03:01:30 trying to load the bigger model
   
   03:13:00 python readinto
   
   03:16:20 load only 13GB because of gc
   
   03:18:20 making copy = bad
   
   03:20:00 apple m1, m2 max, ultra memory
   
   03:21:30 v.shape, tensors
   
   03:23:00 real offer sponsor, tinycorp honest corp
   
   03:32:10 millionaire
   
   03:34:50 bad chatter, DEBUG=3, pointer, constant folded
   
   03:38:40 the problem and easy fix, mailing the cookie for anyone who knows, thai food
   
   03:44:30 what type is the output buffer
   
   03:47:45 does not use ram because of fake tensors
   
   03:49:55 mid model, loading 13B weight model
   
   03:55:30 bad chat WEIGHTS=0
   
   03:59:30 closing apps, chrome, discord
   
   04:01:50 mac process disable swap, metal buffer force ram resident
   
   04:05:00 force os x buffer to not swap, metal makr bugger as not swap, MTLResourceStorageModeShared
   
   04:09:55 mac os x disable swap for single process, apple gpu supported types, pci-e 4 16x bandwidth
   
   04:16:20 improving prompts, strassen algorithm
   
   04:23:00 let's go
   
   04:27:25 getting food
   
   04:35:00 marc andreessen
   
   04:43:00 who is stacy
   
   04:48:40 git commit add gary
   
   04:49:00 context infinite
   
   04:49:20 gary vs stacy
   
   04:49:40 ai george hotz disappointment
   
   04:50:20 stacy saying thanks for watching
   
   04:51:00 llama branch 24GB ram min requirement, having fun with stacy this weekend

2. do you annotate all your videos or youtube does that automatically

3. Maybe you should've preprompted it more to not give short answers and "I don't know". I think also once it says it doesn't know it will just keep repeating that. I have no idea if it's possible, but if you could do something like negative prompts (like in stable diffusion) here you could give examples of answers you don't want.

4. How did you learn to code AI?

5. Having the stream comments in closed caption is a nice touch!

6. Nah 1:42:44 LMAOO

7. he eats like his personality

8. Hi, I hope you do it for maide in Brazil car models like Jeep Commander Overland TD380 4×4. Here, we have a huge market waiting for you.

9. Hi , can you make one video about how to setup vscode with vim configuration, and settings.

10. Hi , can you make one video about how to setup vscode with vim configuration, and settings.

11. Hi , can you make one video about how to setup vscode with vim configuration, and settings.

12. Hi , can you make one video about how to setup vscode with vim configuration, and settings.

13. Hi , can you make one video about how to setup vscode with vim configuration, and settings.

14. llama.cpp is also super-easy to run on an M1 processor. I was able to run the 13B and 30B models on a 32GB M1 MAX

15. at this point i often put your videos as background for put to sleep / meditation practices. and i don't even know how to program

16. 17:16

17. I love how George dodge the question of the chatter with "l want food",
    this reminds of what an AI researcher (stuart russel) was saying when asking things to people in the field :
    That it looks like everytime the risk was underlined, people were automatically discarding whatever serious safety question by "yeah just turn it off", or "nah I don't know we'll figure it out".
    Come on George, you're better than that aren't you ?

    Tho you're defo one of the good guys.

18. I am Gary

19. What's tiny grad ??????

20. Can you program me software for debian that spoofs my device so if I go to a device info checker website they will think I use IOS? I am poor but I can pay you 300 for it sometime this year after one of my paychecks if you are interested. I'd like to make it available to everyone on my website too, I'd make sure to put your name on it and make a whole video glorifying you as a computer God. 😂

21. Glad to see you are still coding. Keep it up brother. You are the best. ❤

22. if you add voice interface i gona buy license 🙂

23. The HotzGPT

24. Can humanity expand its activities in a limited space? Brilliant brains must find a way to better deter those with destructive brains…

Comentários estão fechados.