Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always…
Read the full articleYou might also wanna read
Gemini Function Calling
A promising feature of the Gemini large language model released recently by Google DeepMind , is the support for function calls . It’s a way
Amplitude Gating: A Non-Destructive FFN Intervention Method for Improving Tool-Structured LLM Outputs
Large language models increasingly operate as tool-using agents, where small format, argument, or function-call errors can invalidate otherw
arxiv.org·3d agoGemini, Google's Large Language Model, for Java Developers
As a follow-up to my talk on generative AI for Java developers , I’ve developed a new presentation that focuses more on the Gemini large mul
How we built the most performant DeepSeek V3.2, MiniMax-M2.5 and Qwen 3.5 397B on DigitalOcean Serverless Inference
Today at Deploy, we are announcing the general availability of DeepSeek V3.2, MiniMax-M2.5, and Qwen 3.5 397B on DigitalOcean Serverless Inf
Gemini codelab for Java developers using LangChain4j
No need to be a Python developer to do Generative AI! If you’re a Java developer, you can take advantage of LangChain4j to implement some ad
DigitalOcean Serverless Inference: A Deep Dive
The Problem: Inference Gets Hard at Scale If you’ve shipped an AI feature to production, you already know: the hard part isn’t making a mode
Comments
Sign in to join the conversation.
No comments yet. Be the first.