Downloads · 30 days
6
16% of all-time downloads
imdatta0/qwen3-4b-swegym-moto-kl02-sft20k-hardmulti-qwen36scheduler-capped-v1-adapter
qwen3-4b-swegym-moto-kl02-sft20k-hardmulti-qwen36scheduler-capped-v1-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.
LoRA adapter checkpoint from the Qwen3 GRPO patch investigation on SWE-Gym Moto tasks.
Downloads · 30 days
6
16% of all-time downloads
All-time downloads
38
Public
Repo size
144 MB
Likes
0
Public
Click a slice to open those files.
.safetensors132 MB · 92%
From the Hugging Face model README
LoRA adapter checkpoint from the Qwen3 GRPO patch investigation on SWE-Gym Moto tasks.
This is a durability upload for the qwen36scheduler-capped-v1 continuation, not a promoted frontier checkpoint.
It starts from the prior hard-multi SFT adapter and adds a capped teacher mix containing Qwen3.6 scheduler analog rows.
/mnt/disks/unslothai/datta0/cache/qwen3-grpo-patch/20260605_125656_swegym_q4b-kl02-sft20k-hardmulti-qwen36scheduler-capped-v1_ee83de6/checkpoints/best_holdout
20260605_125656_swegym_q4b-kl02-sft20k-hardmulti-qwen36scheduler-capped-v1_ee83de6post_sftruns/distill_hardmulti20k_plus_qwen36scheduler_capped_v1/sft_pass.jsonl/mnt/disks/unslothai/datta0/cache/qwen3-grpo-patch/20260605_045145_swegym_q4b-kl02-sft20k-hardmulti_10e3a3b/checkpoints/best_holdout7/35, mean reward 0.3706, patch-applied rate 25/35Use with the matching Qwen3-4B Instruct base model and the repo's search/replace SWE-Gym evaluation harness. The checkpoint has not replaced the hard-multi SFT frontier unless later pass@8 evaluation proves otherwise.