Downloads · 30 days
5
14% of all-time downloads
imdatta0/qwen3-4b-swegym-moto-kl02-sft20k-hardmulti-interp-teachergap-v1-alpha025-adapter
qwen3-4b-swegym-moto-kl02-sft20k-hardmulti-interp-teachergap-v1-alpha025-adapter is a text generation model from imdatta0. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
This repository contains a PEFT LoRA adapter for unsloth/Qwen3-4B-Instruct-2507.
Downloads · 30 days
5
14% of all-time downloads
All-time downloads
36
Public
Repo size
132 MB
Likes
0
Public
Click a slice to open those files.
.safetensors132 MB · 100%
From the Hugging Face model README
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.
Held-out sample seed 9012, k=1 smoke:
| adapter | context | seed | greedy | selected@1 | any-of-1 | single any | multi any |
|---|---|---|---|---|---|---|---|
| hard-multi/teacher-gap interp alpha 0.25 | 20k | 9012 | 8/35 | 10/35 | 11/35 | 9/18 | 2/17 |
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.
adapter_model.safetensors: PEFT LoRA adapter weightsadapter_config.json: PEFT adapter configurationtokenizer_config.json: tokenizer configurationinterp_meta.json: local interpolation metadataThe base model weights are not included.