Downloads · 30 days
0
qwen2.5-0.5b-sql-qlora
aijadugar/qwen2.5-0.5b-sql-qlora
qwen2.5-0.5b-sql-qlora is a machine learning model from aijadugar. 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. The card lists the license as apache-2.0.
This model is Qwen/Qwen2.5-0.5B-Instruct fine-tuned on a small slice of b-mc2/sql-create-context using QLoRA: a 4-bit (NF4) quantized frozen base model via bitsandbytes, with a LoRA adapter (rank=8, alpha=16) trained…
Access
Public
Updated Aug 21, 2026
Parameters
494M
741 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors730 MB · 98%
Parameter types
How the weights are stored.
U8358M · 72%
Base models
Model card
From the Hugging Face model README
Qwen2.5-0.5B-Instruct fine-tuned with QLoRA (Text-to-SQL)
This model is Qwen/Qwen2.5-0.5B-Instruct fine-tuned on a small slice of
b-mc2/sql-create-context using QLoRA: a 4-bit (NF4) quantized frozen
base model via bitsandbytes, with a LoRA adapter (rank=8, alpha=16)
trained on top via peft, then merged back into full precision.
Training details
- Base model:
Qwen/Qwen2.5-0.5B-Instruct, loaded in 4-bit NF4 with double quantization - Method: QLoRA (rank=8, alpha=16), applied to
q_proj, k_proj, v_proj, o_proj - Dataset: 250 examples from
b-mc2/sql-create-context - Hardware: Kaggle, 1x Tesla T4
How to use
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("YOUR_USERNAME/YOUR_REPO_NAME")
tokenizer = AutoTokenizer.from_pretrained("YOUR_USERNAME/YOUR_REPO_NAME")
This model is a learning exercise, not a production system -- expect rough edges.
- Library
- peft
- Type
- qwen2
- License
- apache-2.0
- Created
- Aug 21, 2026
- Updated
- Aug 21, 2026