@maximelabonne: Small decision models can be insanely good when fine-tuned. We played with d1-omni-600M and it can destroy any model on…
Summary
Maxime Labonne highlights that small decision models like d1-omni-600M can be extremely effective when fine-tuned, with Leonie sharing notebooks on fine-tuning the d1-3B decision model using Unsloth and Hugging Face TRL in 30 minutes on a free-tier GPU.
View Cached Full Text
Cached at: 10/17/26, 04:47 AM
Small decision models can be insanely good when fine-tuned.
We played with d1-omni-600M and it can destroy any model on the games + format (state, input) you train it on.
leonie (@helloiamleonie): how do you fine-tune a decision model on your own data?
in these two notebooks, you’ll learn: • how to prepare the training data • how to fine-tune our d1-3B decision model • using @UnslothAI and @huggingface TRL
all within 30 minutes on a free-tier GPU.
unsloth:
Similar Articles
d3-edge (0.6B) fine-tuned outperformed d3 (27B) decision model
A 0.6B parameter d3-edge model, fine-tuned with SFT + LoRA on a few thousand examples, outperformed the 27B d3 decision model on typed decisions and nearly matched it on Banking77, highlighting the value of fine-tuning small specialized models over large general-purpose ones.
@Aurelien_L_: I'm kinda surprised decision models didn't blow up earlier tbh. Super happy we got to release our take on this with d1,…
Liquid AI announced d1, their first decision model, which outperforms Jev on Hugging Face's Decision Index with advantages in multilingual evaluations, robustness, and handling longer inputs.
@heyshrutimishra: AI models are getting small enough to make real-time decisions directly on your devices. Liquid AI just released two op…
Liquid AI released Open d1, two open-weight multimodal decision models (d1-3B and d1-omni-600M) enabling real-time inference directly on devices, with the 3B model achieving 8ms decision latency on an RTX 4090 and 50ms on a Jetson Orin Nano.
@omarsar0: Small models are getting really good at reasoning. It's exciting because SLMs can unlock so much at the harness layer. …
TheWebAI released TwIL-LM3-Pro, a 3.6B-parameter open-source SLM that runs locally and achieves 95.4 on BIG-Bench Hard, outperforming Qwen3-8B's 63.7, using a post-training recipe of formal-logic fine-tuning, weight merging, and RL with a programmatic verifier.
Open d1: Edge decision models for text, vision, and audio (6 minute read)
Liquid AI 发布了 d1 决策模型家族的两款开放权重模型 d1-3B 和 d1-omni-600M，支持文本、视觉和音频模态，通过单次前向传递直接输出答案，在 Decision Index 上超越同规模模型并可在 NVIDIA Jetson 边缘设备上实现实时推理。