Downloads · 30 days
10
22% of all-time downloads
kacperwikiel/slayer-v48-qwen3.5-27b
slayer-v48-qwen3.5-27b is a machine learning model from kacperwikiel. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as other.
LoRA adapter for Qwen/Qwen3.5-27B trained for Polish Open PL style tasks.
Downloads · 30 days
10
22% of all-time downloads
All-time downloads
45
Public
Repo size
658 MB
Likes
0
Public
Click a slice to open those files.
.safetensors638 MB · 97%
From the Hugging Face model README
LoRA adapter for Qwen/Qwen3.5-27B trained for Polish Open PL style tasks.
This adapter should be treated as a research checkpoint unless the attached evaluation artifacts show it was explicitly promoted.
/home/ubuntu/runs/qwen35_27b_sft_openpl_style_v48_full_v43_epoch_lr2e-6_steps14832_seed48027_loranot recordedn/anot attached65.93The Bielik number is a published leaderboard target, not a same-harness local Bielik run, unless a separate same-harness Bielik artifact is attached.
The repository may include:
eval/result_summary.jsoneval/open_pl_average.jsoneval/compare_vs_v31_broad_closed200.jsoneval/compare_vs_v48_broad_closed200.jsoneval/compare_vs_bielik_cached_broad_closed200.jsoneval/promotion_decision.jsonThese are local proxy artifacts. Do not report them as official leaderboard results without a full official evaluation.
v48 Qwen3.5-27B LoRA full v43-epoch SFT. Best slayer to date; closed non-RAG present avg 69.91 (>v31 63.29, >Bielik target 65.93).
{
"improved": 28,
"metrics": 38,
"missing": 0,
"regressed": 8,
"unchanged": 2
}