First attempt at improving reasoning abilities for Qwen3.5 4b model based on the open
crownelius/Opus-4.6-Reasoning-3300x dataset.
I didn't have the patience to run too many evals, but I definitely noticed vibes wise it was a lot more "opus"-like (in a good way) in it's reasoning and responses, base Qwen3.5 4b kinda rambles on. Seemed smarter... The one eval I did was was the latest
LiveBench Reasoning benchmarks, and here are the results:
For v2 of this model, I need to fix the thinking template. It seems like the model ALWAYS does reasoning due to the way I templated the dataset, so I'm doing another training run with explicit think or no think rows. (hopefully that works?).
Also, I don't know much about training models or ML, I'm a Software Engineer who uses a lot of AI. I just started, and this was pretty much the first real model I've ever trained, so please be nice!
I trained this on a single RTX 4060ti with 16GB VRAM, took around 2 or 3 hours.
