Downloads · 30 days
0
qwen-kazsandra-homework
Ualikhan888/qwen-kazsandra-homework
qwen-kazsandra-homework is a machine learning model from Ualikhan888. 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 LoRA adapter fine-tuned on the KazSANDRA dataset for sentiment classification.
Access
Public
Updated Apr 22, 2026
Repo size
34.9 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors34.9 MB · 75%
At a glance
- Access
- Public
- Created
- Apr 22, 2026
- Updated
- Apr 22, 2026
- SHA
- 8182a5be
Model card
From the Hugging Face model README
Qwen KazSANDRA LoRA Adapter
This repository contains a LoRA adapter fine-tuned on the KazSANDRA dataset for sentiment classification.
Model
- Base model: Qwen2.5-1.5B-Instruct
- Method: LoRA fine-tuning
- Task: Binary sentiment classification (negative / positive)
Training
Two configurations were tested:
- Config A: r=8, alpha=16
- Config B: r=32, alpha=64 (best)
The best configuration achieved higher accuracy on validation data.
Results
Best configuration:
- r = 32
- alpha = 64
- accuracy ≈ 0.69
Compared to:
- r = 8, alpha = 16 → accuracy ≈ 0.62
The larger LoRA rank showed better performance.
Usage
from peft import PeftModel
from transformers import AutoModelForCausalLM
base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct")
model = PeftModel.from_pretrained(base, "Ualikhan888/qwen-kazsandra-homework")
- Created
- Apr 22, 2026
- Updated
- Apr 22, 2026