Downloads · 30 days
0
qwen-3b-sft
SaiTejaSrivilli/qwen-3b-sft
qwen-3b-sft is a machine learning model from SaiTejaSrivilli. 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 apache-2.0.
Fine-tuned version of Qwen2.5-3B-Instruct using Supervised Fine-Tuning with LoRA.
Access
Public
Updated Feb 7, 2026
Repo size
51.8 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors40.4 MB · 72%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Feb 7, 2026
- Updated
- Feb 7, 2026
- SHA
- 6cf946d5
Model card
From the Hugging Face model README
Qwen-3B Fine-tuned with SFT
Fine-tuned version of Qwen2.5-3B-Instruct using Supervised Fine-Tuning with LoRA.
Training Details
- Method: SFT with LoRA (r=8)
- Dataset: UltraFeedback (100 samples)
- Loss: 1.412 → 1.176 (17% improvement)
- Trainable Params: 0.5%
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-3B-Instruct")
model = PeftModel.from_pretrained(base, "SaiTejaSrivilli/qwen-3b-sft")
tokenizer = AutoTokenizer.from_pretrained("SaiTejaSrivilli/qwen-3b-sft")
- License
- apache-2.0
- Languages
- en
- Created
- Feb 7, 2026
- Updated
- Feb 7, 2026