imdatta0/qwen3-4b-swegym-moto-kl02-sft20k-hardmulti-interp-teachergap-v1-alpha025-adapter
05
Qwen3-4B SWE-Gym Moto Hardmulti Teachergap Interpolation Adapter
This repository contains a PEFT LoRA adapter for unsloth/Qwen3-4B-Instruct-2507.
The adapter was produced as an arithmetic interpolation between the Qwen3-4B hard-multi 20k adapter and the teacher-gap-v1 adapter:
hardmulti + 0.25 * (teacher_gap_v1 - hardmulti)It was evaluated on the held-out SWE-Gym Moto search/replace patch task with 20k anchored retrieval context.
Evaluation
Held-out sample seed 9012, k=1 smoke:
This was a negative/non-frontier checkpoint. It loaded and evaluated cleanly, but it did not recover the teacher-gap-v1 multi-file tail hit and it underperformed the hard-multi 20k frontier.
Contents
adapter_model.safetensors: PEFT LoRA adapter weightsadapter_config.json: PEFT adapter configurationtokenizer_config.json: tokenizer configurationinterp_meta.json: local interpolation metadata
The base model weights are not included.
