Downloads · 30 days
0
solar11781/lab21-qwen25-3b-finance-lora-r16
lab21-qwen25-3b-finance-lora-r16 is a machine learning model from solar11781. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This repository contains a QLoRA fine-tuned adapter based on:
Downloads · 30 days
0
Access
Public
Updated May 7, 2026
Repo size
26.2 MB
Likes
1
Public
Click a slice to open those files.
.safetensors14.8 MB · 56%
From the Hugging Face model README
This repository contains a QLoRA fine-tuned adapter based on:
unsloth/Qwen2.5-3B-bnb-4bitgbharti/finance-alpacar=16, alpha=32| Rank | Perplexity |
|---|---|
| Base | 7.5904 |
| r=8 | 4.9031 |
| r=16 | 4.7022 |
| r=64 | 4.6937 |
The experiment showed that r=16 gave the best balance between quality and efficiency, while r=64 had diminishing returns.
adapter_model.safetensors — LoRA adapter weightsadapter_config.json — adapter configurationBùi Trần Gia Bảo — 2A202600009