Downloads · 30 days
11
16% of all-time downloads
lab22-dpo-vn
nekloyh/lab22-dpo-vn
lab22-dpo-vn is a machine learning model from nekloyh. 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.
SFT (bkai vi-alpaca, 1k) → DPO (UltraFeedback 2k, beta=0.1, lr=5e-7) trên base Qwen2.5-3B (4-bit QLoRA, Unsloth). Xem repo lab để biết reward curves + side-by-side eval.
All-time downloads
68
Public
Repo size
371 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors120 MB · 91%
At a glance
- Library
- peft
- Access
- Public
- Created
- Jun 30, 2026
- Updated
- Jul 1, 2026
- SHA
- 80175304
Base models
Model card
From the Hugging Face model README
Lab22 DPO-aligned Qwen2.5-3B (VN)
SFT (bkai vi-alpaca, 1k) → DPO (UltraFeedback 2k, beta=0.1, lr=5e-7) trên base Qwen2.5-3B (4-bit QLoRA, Unsloth). Xem repo lab để biết reward curves + side-by-side eval.
- Library
- peft
- Created
- Jun 30, 2026
- Updated
- Jul 1, 2026