Downloads · 30 days
0
twscholar-lm-sft-7b-qlora-r64
Yoda6131027/twscholar-lm-sft-7b-qlora-r64
twscholar-lm-sft-7b-qlora-r64 is a machine learning model from Yoda6131027. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as cc-by-nc-4.0.
QLoRA SFT adapter for Qwen2.5-7B-Instruct on the twscholar-lm dataset — the SFT stage on its own, before DPO. Most users should prefer twscholar-lm-dpo-7b-final (SFT + DPO); this checkpoint is published for reproducib…
Access
Public
Updated Jul 18, 2026
Repo size
334 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors646 MB · 97%
At a glance
- License
- cc-by-nc-4.0
- Access
- Public
- Created
- Jul 18, 2026
- Updated
- Jul 18, 2026
- SHA
- b6467e59
Base models
Model card
From the Hugging Face model README
twscholar-lm — SFT only (intermediate checkpoint)
QLoRA SFT adapter for Qwen2.5-7B-Instruct on the twscholar-lm dataset —
the SFT stage on its own, before DPO. Most users should prefer
twscholar-lm-dpo-7b-final (SFT + DPO); this checkpoint is published for
reproducibility and for anyone studying the SFT-vs-SFT+DPO comparison
directly.
- r=64, alpha=128, 1 epoch (see the main model card / project repo for why
1 epoch was chosen over 3 —
results/m4_ood_glitch_investigation.md) - Full project: https://github.com/oscarlin778/twscholar-lm
- License: cc-by-nc-4.0 (inherited from the training dataset)
- License
- cc-by-nc-4.0
- Languages
- zh
- Created
- Jul 18, 2026
- Updated
- Jul 18, 2026