Is this somehow based on Temple OS?
No but each version of L2E OS has a name. v0.1 is the first version and we wanted to pay our tribute to Terry A Davis, so called it TempleDOS and added a bit of TempleOS references.
Llama 2 Everywhere (L2E): Standalone, Binary Portable, Bootable Llama 2
21–30 of 58 posts
Re: Llama 2 Everywhere (L2E): Standalone, Binary Portable, Bootable Llama 2
#22Creator here. Thank you for sharing!
This is hilarious (in a good way), I love it. Thanks for creating it.
Re: Llama 2 Everywhere (L2E): Standalone, Binary Portable, Bootable Llama 2
#23Creator here. Thank you for sharing!
Can one write installable apps for this OS that Llama can call out to?
We need to go deeper!
Re: Llama 2 Everywhere (L2E): Standalone, Binary Portable, Bootable Llama 2
#24Re: Llama 2 Everywhere (L2E): Standalone, Binary Portable, Bootable Llama 2
#25Earlier quoted context omitted.
thanks! I am still curious about the sensor inputs part. I am trying to replace the 2.4ghz controller on my electric skateboard to make 0 to 5kmh and braking more pleasant and maybe use gyroscopes to do away with the controller altogether. What would tokens be in that case? Do you create a CAN style representation and feed that to the llm? What kind of throughput do you foresee being possible on which hardware?
I am still thinking how I'll pull this off. But basically it is collect tons of Telemetry converted to in ascii/text. Telemetry in sense sensor streams, both command and responses. Then we'll just train a small model for long enough. Then we will see how it would respond. That's the plan sort of.
In this case, I would ask the LLM to suggest an algorithm to minimize acceleration, jerk and snap based on the expected sensor input data, and then just implement that. Probably in memory on whatever runs the board.
Straightforward control problem of bringing the board from 5-0kmh smoothly?
Re: Llama 2 Everywhere (L2E): Standalone, Binary Portable, Bootable Llama 2
#26very weird, i like it.
Re: Llama 2 Everywhere (L2E): Standalone, Binary Portable, Bootable Llama 2
#27Earlier quoted context omitted.
It's the name of the project - Llama2Everywhere.
thanks! I am still curious about the sensor inputs part. I am trying to replace the 2.4ghz controller on my electric skateboard to make 0 to 5kmh and braking more pleasant and maybe use gyroscopes to do away with the controller altogether. What would tokens be in that case? Do you create a CAN style representation and feed that to the llm? What kind of throughput do you foresee being possible on which hardware?
Basic control theory will work better than AI here. The mathematical models used in control theory have been used in computing since at least the 50's (Kalman Filters). I suspect you won't have issues with computational power.
Figuring out exactly which model to use and how, may take some work. Also understanding control theory will allow you to do things like traction control, etc.
Re: Llama 2 Everywhere (L2E): Standalone, Binary Portable, Bootable Llama 2
#28No specified of memory or processing requirements? How do I know if it will work on my machine?
Re: Llama 2 Everywhere (L2E): Standalone, Binary Portable, Bootable Llama 2
#29No specified of memory or processing requirements? How do I know if it will work on my machine?
Sorry there. It's 512MB RAM & x86_64 CPU. This just an alpha version so not very usable :)
Re: Llama 2 Everywhere (L2E): Standalone, Binary Portable, Bootable Llama 2
#30Earlier quoted context omitted.
thanks! I am still curious about the sensor inputs part. I am trying to replace the 2.4ghz controller on my electric skateboard to make 0 to 5kmh and braking more pleasant and maybe use gyroscopes to do away with the controller altogether. What would tokens be in that case? Do you create a CAN style representation and feed that to the llm? What kind of throughput do you foresee being possible on which hardware?
Basic control theory will work better than AI here. The mathematical models used in control theory have been used in computing since at least the 50's (Kalman Filters). I suspect you won't have issues with computational power. Figuring out exactly which model to use and how, may take some work. Also understanding control theory will allow you to do things like traction control, etc.
In addition. I Agree.