Downloads · 30 days
4
18% of all-time downloads
rswan-llm-lora
TokyoEye/rswan-llm-lora
rswan-llm-lora is a machine learning model from TokyoEye. 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 mit.
Proven on T1000 4GB. Qwen2-0.5B-Instruct + LoRA r=4 α=8 on nyu-mll/glue sst2 200/40 @64, batch 2 eff 8, 1 epoch, bf16.
All-time downloads
22
Public
Repo size
2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt989 MB · 50%
At a glance
- Library
- peft
- License
- mit
- Access
- Public
- Created
- Aug 29, 2026
- Updated
- Aug 29, 2026
- SHA
- a14e623b
Base models
Model card
From the Hugging Face model README
rswan-llm-lora v3 — sweep-best val/loss 0.5804 (r=4)
Proven on T1000 4GB. Qwen2-0.5B-Instruct + LoRA r=4 α=8 on nyu-mll/glue sst2 200/40 @64, batch 2 eff 8, 1 epoch, bf16.
- Registry: rswan-llm-lora v3 (mlflow 9db5245cd0394a478c9934aa4b85efdf, hermes/llm-lora sweep hermes-llm-lora-v1 trial 004)
- Metrics: train/loss 1.0963 (prior single) vs sweep-best val/loss 0.5804 val/acc 0.70
- Sweep parent 919de78a9554471892f314e25ebaeceb; v4 (hermes-llm-lora-v2) proves gated auto-promote but 0.7684 regresses — v3 stays SOTA head.
Artifacts: model.pt (torch.save state_dict fallback from mlflow.pytorch.log_model pt2 gate), checkpoints/best.pt Spec: optional-skills/mlops/mlflow-pytorch-trainer/docs/GOVERNED_TRAINER_SPEC.md
- Library
- peft
- License
- mit
- Created
- Aug 29, 2026
- Updated
- Aug 29, 2026