Downloads · 30 days
10
12% of all-time downloads
latkes/rankalign-v7-qwen3.5-9b-ifeval-s2-variance-run2
rankalign-v7-qwen3.5-9b-ifeval-s2-variance-run2 is a text generation model from latkes. Use it when you need the model to write or continue text. It is set up for transformers.
Merged (base + LoRA) Qwen3.5-9B RankAlign (setting s2) model, trained on a fresh RunPod pod to measure run-to-run variance vs the original 83.2 checkpoint (latkes/rankalign-v7-qwen3.5-9b-ifeval-s2-ep2).
Downloads · 30 days
10
12% of all-time downloads
All-time downloads
82
Public
Parameters
9B
18 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors17.9 GB · 100%
From the Hugging Face model README
Merged (base + LoRA) Qwen3.5-9B RankAlign (setting s2) model, trained on a fresh RunPod pod
to measure run-to-run variance vs the original 83.2 checkpoint
(latkes/rankalign-v7-qwen3.5-9b-ifeval-s2-ep2).
Recipe (identical to the original): run_qwen35_cell.sh ifeval s2 —
ranking_loss_ref_fix.py --task ifeval-concat --train_g_or_d g --all --delta 0.15 --delta-bins 10 --preference_loss_weight 1 --semi-supervised 0.1 --validator-log-odds --lora --num_epochs 3. Auto-delta -> 0.96.
Environment (identical to the original): RunPod runpod/pytorch:2.4.0 image
(torch 2.4.1), requirements-gemma4.txt (transformers 5.8.1), Qwen3.5 torch-fallback
attention.
Differs from the original only by the unseeded pair shuffle + GPU nondeterminism — this is
run 2 of 3. LoRA adapter under adapter/, training log cell_ifeval_s2.log.