zils-mini-r2a
A body for the Zils d3-mini soup pool (Bittensor subnet 127): a fine-tune of Qwen/Qwen3.5-4B in the chassis layout, BF16, language weights trained, vision tower from the parent.
Soup fine-tune on relay data: start = uniform average of the two current z3-mini soup bodies; one rank-64 LoRA run (lr 5e-5) on 60,000 random rows, merged.
Training data: 60,000 random rows of the public Zils relay teacher answers (zils-relay-answers: teacher probabilities on public tasksource decision rows, many task families incl. spatial reasoning such as StepGame and SpartQA). No validator exam items and no public seed items were used. This repository holds weights only; check the source datasets terms before reuse.
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support
Model tree for Charlie320/zils-mini-r2a
Base model
Qwen/Qwen3.5-4B-Base Finetuned
Qwen/Qwen3.5-4B Finetuned
Maincode/Matilda-Decision-v1-Mini Finetuned
Charlie320/zils-mini-hx3 Finetuned
Charlie320/zils-mini-s3l