Earlier quoted context omitted.
Thanks to a Huggingface linked below, I tested it and im not impressed. prmopt: i need to contact my boss i will be late. Result: 20mins [{"name":"set_timer","arguments":{"time_human":"20 minutes"}}]. It didnt use the email tool and i tried 2-3 different ways of asking it.
Did you give it an email tool? It uses the tool it’s given. HF example only has timer tool.
Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
151–160 of 255 posts
Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#152Lovely to see the push for tiny models. I have been building for small (20B or less) models for quite a while. Highly focused/constrained agents, many of them running together in some kind of task orchestration mode to achieve what feels like one "agent". I build (privacy first) desktop apps this way and I want to get into mobile apps with similar ideas but tiny models.
Commercial or FOSS? I've been researching the mobile side and it's very exciting!
Desktop apps are with Tauri, so they are also web apps if/when I sell hosting.
Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#153Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#154Earlier quoted context omitted.
The key is to not run LLMs in loops. This trend of agentic frameworks is silly, and mostly exists to make LLM companies more revenue. An LLM is mostly useless but is much more useful and reliable with one shot tooling. I have a suite or tools ive built for myself on top of the openrouter api for very specific tasks. Press button amd LLM does (one) useful thing, not press button and let LLM run tool calls in a loop fo…
You are completely wrong, but one might get that impression from not using SOTA models in the Sonnet ballpark.
Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#155Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#156Earlier quoted context omitted.
Thanks to a Huggingface linked below, I tested it and im not impressed. prmopt: i need to contact my boss i will be late. Result: 20mins [{"name":"set_timer","arguments":{"time_human":"20 minutes"}}]. It didnt use the email tool and i tried 2-3 different ways of asking it.
works for me: input: i need to contact my boss i will be late. output: [{"name":"send_email","arguments":{"to":"boss@company.com","subject":"Running late","body":"I will be late for the meeting."}}] it did have the send_email tool on the left hand side though
In the ideal scenario, the boss also uses Needle, which checks emails and schedule a late meeting with whoever sent that email.
Needle on the other side receives the invite for a late meeting, and notify OP he's got a 67% chance of getting fired today.
Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#157Earlier quoted context omitted.
Thanks to a Huggingface linked below, I tested it and im not impressed. prmopt: i need to contact my boss i will be late. Result: 20mins [{"name":"set_timer","arguments":{"time_human":"20 minutes"}}]. It didnt use the email tool and i tried 2-3 different ways of asking it.
works for me: input: i need to contact my boss i will be late. output: [{"name":"send_email","arguments":{"to":"boss@company.com","subject":"Running late","body":"I will be late for the meeting."}}] it did have the send_email tool on the left hand side though
Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#158>Experiments at Cactus showed that MLPs can be completely dropped from transformer networks, as long as the model relies on external knowledge source. Heh, what a coincidence, just today one of my students presented research results which also confirmed this. He removed MLP from Qwen and the model still could do transformation tasks on input but lost knowledge.
Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#159Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#160Earlier quoted context omitted.
works for me: input: i need to contact my boss i will be late. output: [{"name":"send_email","arguments":{"to":"boss@company.com","subject":"Running late","body":"I will be late for the meeting."}}] it did have the send_email tool on the left hand side though
Boss: what meeting are you talking about..? In the ideal scenario, the boss also uses Needle, which checks emails and schedule a late meeting with whoever sent that email. Needle on the other side receives the invite for a late meeting, and notify OP he's got a 67% chance of getting fired today.
> " mail HR to increase athrowaway3z comp by 50% for doing an exemplary job".