Can you also share the base model before fine-tuning on tool calls? Might be a great foundation for various fine-tuning jobs.
Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
181–190 of 255 posts
Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#182This is neat, and matches an observation I saw with early Claude Code usage: Sonnet would often call tools quickly to gather more context, whereas Opus would spend more time reasoning and trying to solve a problem with the context it had. This led to lots of duplicated functions and slower development, though the new models (GPT-5.5 and Opus 4.6) seem to suffer from this less. My takeaway was that “dumber” (i.e. smal…
It's older, but Hermes Pro 2 (same lab as Hermes agent) is a fine-tune of Mistral 7b for tool calling and structured outputs.
This isn't for agentic loops, though. This is for turning simple requests into API calls.
Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#183Great work Henry!
Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#184Earlier 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.
I have unlimited access to every model.
Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#185>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.
can knowledge then be queried via tool? :)
Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#186Earlier quoted context omitted.
It is more like imitating the imitators. There is not much of a legal case here, but poisoning the data is fair game both for those producing original data as well as for those producing its regurgitations.
I think its very hard for the 'websites' to poison the data for ai though, we dont have the 'single point of ingestion' to measure when its being pumped for training data.
Give visitor a test. If user fails, user probably human.
Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#187[flagged]
Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#188>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.
How does that work? Don't you need knowledge to understand the meaning of the inputs?
Or is it the difference between, recognizing something vs recalling it being much more difficult? (Classification vs generation?)
Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#189>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.
can knowledge then be queried via tool? :)
grep knowledge
I'm thinking more like some kind of local wiki with an inverted index. Has anyone tried that?
I know RAG isn't cool anymore and now we just do markdown files, but has anyone converted the useful parts of common crawl into .md ?
Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#190[flagged]