Does the model have capacity for in context learning ?, if we give it examples of patterns can it follow them ?.
Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
41–50 of 255 posts
Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#42FYI, 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)."
FYI, Gemini was developed using stolen copyrighted works without author consent. The double standard is striking.
Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#43Earlier quoted context omitted.
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.
Deployed it to a huggingface space: https://huggingface.co/spaces/benoitfavre/needle-playground You can check the very simple docker file there.
Here's the Dockerfile, it's delightfully simple https://huggingface.co/spaces/benoitfavre/needle-playground/...
Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#44Earlier quoted context omitted.
Alternatively, record a video that showcases it.
Ok, will do that now!
I know we all think of bad things when we hear "short form video" but short demos can do a LOT for any project, shows the user how its used, what it looks like, what it solves, etc all in anywhere from 15 seconds to a couple of minutes, doesn't need to be ultra fancy, screen recording is fine. :)
Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#45Earlier quoted context omitted.
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.
Deployed it to a huggingface space: https://huggingface.co/spaces/benoitfavre/needle-playground You can check the very simple docker file there.
Thanks!
Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#46Earlier quoted context omitted.
Ok, will do that now!
I know we all think of bad things when we hear "short form video" but short demos can do a LOT for any project, shows the user how its used, what it looks like, what it solves, etc all in anywhere from 15 seconds to a couple of minutes, doesn't need to be ultra fancy, screen recording is fine. :)
Yes, a demo might be a good idea.
Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#47Is the idea here to add function calling to models that don't have it, or even improve function calling (qwen quirks)?
So it’s a tiny model capable of function calling that could run locally on cheap devices.
Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#48Can it summarize text it fetches?
Come to think of it, this could be a nice model to have as the first pass in a more complex agent system where Needle hands of the results of a tool call to a larger model.
I will defiantly play around with this!
Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#49Does the model have capacity for in context learning ?, if we give it examples of patterns can it follow them ?.
Not yet, for now. But it’s in the works!
Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#50Earlier quoted context omitted.
Ok, will do that now!
I know we all think of bad things when we hear "short form video" but short demos can do a LOT for any project, shows the user how its used, what it looks like, what it solves, etc all in anywhere from 15 seconds to a couple of minutes, doesn't need to be ultra fancy, screen recording is fine. :)
Since there is no GUI here, I feel like a simple plaintext chat transcript would be both 100x smaller and 100x easier to read. (Not to mention accessible.)