A brief history of LLaMA models
agi-sphere.com
A brief history of LLaMA models
1–10 of 87 posts
Re: A brief history of LLaMA models
#2There is also CodyCapybara (7B finetuned on code competitions), the "uncensored" Vicuna, OpenAssistant 13B (which is said to be very good), various non English tunes, medalpaca... the release pace maddening.
Re: A brief history of LLaMA models
#3I'm running Vicuna (a LLaMA variant) on my iPhone right now. https://twitter.com/simonw/status/1652358994214928384
The same team that built that iPhone app - MLC - also got Vicuna running directly in a web browser using Web GPU: https://simonwillison.net/2023/Apr/16/web-llm/
Re: A brief history of LLaMA models
#4There needs to be a slight dedicated to tracking all these models with regular updates.
Re: A brief history of LLaMA models
#5I'm running Vicuna (a LLaMA variant) on my iPhone right now. https://twitter.com/simonw/status/1652358994214928384 The same team that built that iPhone app - MLC - also got Vicuna running directly in a web browser using Web GPU: https://simonwillison.net/2023/Apr/16/web-llm/
With all these new AI models, both stable diffusion and llama specially, I'm considering switching to iPhone. I don't think I fully understand why iPhones and Macs are getting so many implementations but it seems like it's hardware based.
Re: A brief history of LLaMA models
#6I'm running Vicuna (a LLaMA variant) on my iPhone right now. https://twitter.com/simonw/status/1652358994214928384 The same team that built that iPhone app - MLC - also got Vicuna running directly in a web browser using Web GPU: https://simonwillison.net/2023/Apr/16/web-llm/
With all these new AI models, both stable diffusion and llama specially, I'm considering switching to iPhone. I don't think I fully understand why iPhones and Macs are getting so many implementations but it seems like it's hardware based.
Homogenized hardware I assume, this is why iOS had so many photography Apps too.
Re: A brief history of LLaMA models
#7I'm running Vicuna (a LLaMA variant) on my iPhone right now. https://twitter.com/simonw/status/1652358994214928384 The same team that built that iPhone app - MLC - also got Vicuna running directly in a web browser using Web GPU: https://simonwillison.net/2023/Apr/16/web-llm/
With all these new AI models, both stable diffusion and llama specially, I'm considering switching to iPhone. I don't think I fully understand why iPhones and Macs are getting so many implementations but it seems like it's hardware based.
iPhones leaned in to "computational photography" a long time ago. Eventually they added custom hardware to handle all the matrix multiplies efficiently. They exposed some of it to apps with an API called CoreML. They've been adding more features like on-device photo tagging, voice recognition, VR stuff.
Re: A brief history of LLaMA models
#8I'm running Vicuna (a LLaMA variant) on my iPhone right now. https://twitter.com/simonw/status/1652358994214928384 The same team that built that iPhone app - MLC - also got Vicuna running directly in a web browser using Web GPU: https://simonwillison.net/2023/Apr/16/web-llm/
With all these new AI models, both stable diffusion and llama specially, I'm considering switching to iPhone. I don't think I fully understand why iPhones and Macs are getting so many implementations but it seems like it's hardware based.
My understanding is that part of it is that Apple Silicon shares all available RAM between CPU and GPU.
I'm not sure how many of these models are actively taking advantage of that architecture yet though.
Re: A brief history of LLaMA models
#9There is also CodyCapybara (7B finetuned on code competitions), the "uncensored" Vicuna, OpenAssistant 13B (which is said to be very good), various non English tunes, medalpaca... the release pace maddening.
And let's not forget about Alpacino (offensive/unfiltered model).
Re: A brief history of LLaMA models
#10It keeps saying the phrase “model you can run locally”, but despite days of trying, I failed to compile any of the GitHub repos associated with these models.
None of the Python dependencies are strongly versioned, and “something” happened to the CUDA compatibility of one of them about a month ago. The original developers “got lucky” but now nobody else can compile this stuff.
After years of using only C# and Rust, both of which have sane package managers with semantic versioning, lock files, reproducible builds, and even SHA checksums the Python package ecosystem looks ridiculously immature and even childish.
Seriously, can anyone here build a docker image for running these models on CUDA? I think right now it’s borderline impossible, but I’d be happy to be corrected…