thanks, yeah, the problem is just handling scale, we don't have the infra ready to go, but anyone can do that. Its easy for people to run on their laptops straight up. Will try the VPS route.
Can this be a Siri-like core? Set me a timer, tell me what’s the weather, etc. Here is transcribed text and available list of tools for the model to call, and voice the output.
Hmm.. this might make it feasible to build something like a command line program where you can optionally just specify the arguments in natural language. Although I know people will object to including an extra 14 MB and the computation for "parsing" and it could be pretty bad if everyone started doing that.
But it's really interesting to me that that may be possible now. You can include a fine-tuned model that understands how to use your program.
E.g. `> toolcli what can you do` runs `toolcli --help summary`, `toolcli add tom to teamfutz group` = `toolcli --gadd teamfutz tom`
FYI, distilling Gemini is explicitly against the ToS:
"You may not use the Services to develop models that compete with the Services (e.g., Gemini API or Google AI Studio). You also may not attempt to reverse engineer, extract or replicate any component of the Services, including the underlying data or models (e.g., parameter weights)."
Suggestion: publish a live demo of the "needle playground". It's small enough that it should be pretty cheap to run this on a little VPS somewhere!
Should be quick and easy with WebGPU, too.
Good idea. Could you make that.
thanks, yeah, the problem is just handling scale, we don't have the infra ready to go, but anyone can do that. Its easy for people to run on their laptops straight up. Will try the VPS route.
Alternatively, record a video that showcases it.
Ok, will do that now!
Can this be a Siri-like core? Set me a timer, tell me what’s the weather, etc. Here is transcribed text and available list of tools for the model to call, and voice the output.
Looks like you need to open up access to https://huggingface.co/Cactus-Compute/datasets/needle-tokeni... - I get this error when trying to run the steps in your README:
> Repository Not Found for url: http s://huggingface.co/api/datasets/Cactus-Compute/needle-tokenizer/revision/main.
Fixed now, apologies!
Thanks, works now: https://gisthost.github.io/?4ff455792651fe755265b467800f47f3
Hmm.. this might make it feasible to build something like a command line program where you can optionally just specify the arguments in natural language. Although I know people will object to including an extra 14 MB and the computation for "parsing" and it could be pretty bad if everyone started doing that.
But it's really interesting to me that that may be possible now. You can include a fine-tuned model that understands how to use your program.
E.g. `> toolcli what can you do` runs `toolcli --help summary`, `toolcli add tom to teamfutz group` = `toolcli --gadd teamfutz tom`
So Needle is trained for INT4, what you see in the playground is INT4, only 14MB, same challenge though.
Oh gotcha. Fixed my comment.
This is very cool I'm going to try to carve out some time to try building this into my MOO system ( https://codeberg.org/timbran/moor / https://timbran.org/moor.html ) as alternative command parser front end.
Thanks, let us know how it goes!
FYI, distilling Gemini is explicitly against the ToS:
"You may not use the Services to develop models that compete with the Services (e.g., Gemini API or Google AI Studio). You also may not attempt to reverse engineer, extract or replicate any component of the Services, including the underlying data or models (e.g., parameter weights)."
I think GLM 5.1 or Kimi 2.6 could substitute for this type of purpose.
Oh no! They stole the model weights! Distillation "attacks" is such bullshit