vsan/tiny-pickle-35b

Tiny Pickle

Tiny Pickle is an experimental short LoRA fine-tune of Qwen/Qwen3.6-35B-A3B.

Training

• —1,000 CodeAlpaca examples
• —20 optimisation steps
• —BF16 LoRA
• —LoRA rank: 16
• —Sequence length: 1,024

This is a pipeline experiment, not evidence that the model improves upon the original base model. It has not undergone comprehensive evaluation.