Downloads · 30 days
2
7% of all-time downloads
lfed-qwen2.5-coder-14b-sql-lora-warehouse-r64
KDDSTLC/lfed-qwen2.5-coder-14b-sql-lora-warehouse-r64
lfed-qwen2.5-coder-14b-sql-lora-warehouse-r64 is a machine learning model from KDDSTLC. 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.
Trained on the real DuckDB warehouse schema (maincore, mainanalytics, mainstaging — ~30+ tables) for the Local First Education Data Framework.
All-time downloads
30
Public
Repo size
1.1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.1 GB · 99%
At a glance
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Jun 23, 2026
- Updated
- Jun 23, 2026
- SHA
- dfcd77dc
Base models
Model card
From the Hugging Face model README
LFED SQL Assistant v2 — Qwen2.5-Coder-14B-LoRA (Warehouse r=64)
Trained on the real DuckDB warehouse schema (main_core, main_analytics, main_staging — ~30+ tables) for the Local First Education Data Framework.
Differences from v1
| v1 (r=32) | v2 (r=64) | |
|---|---|---|
| Training schema | 5 synthetic tables | Real warehouse (~30 tables) |
| LoRA rank | 32 | 64 |
| Adapter size | ~551 MB | ~1.1 GB |
| Target tables | students, enrollment, attendance, discipline, grades | main_core., main_analytics., main_staging.* |
Intended use
Converts natural-language questions about K-12 school data into read-only DuckDB SQL queries. Designed for the LFED Gradio app.
Training data
Synthetic NL→SQL pairs generated against the real warehouse schema using Qwen2.5-72B-Instruct-AWQ via vLLM on Modal A100-80GB. Every generated SQL was validated by executing it against the real DuckDB warehouse.
How to use
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
base = "unsloth/qwen2.5-coder-14b-instruct-bnb-4bit"
adapter = "KDDSTLC/lfed-qwen2.5-coder-14b-sql-lora-warehouse-r64"
model = AutoModelForCausalLM.from_pretrained(base, device_map="auto")
model = PeftModel.from_pretrained(model, adapter, torch_device="cpu")
tokenizer = AutoTokenizer.from_pretrained(adapter)
Known limitations
- Trained on synthetic data against the real schema; may hallucinate columns
- Does not know about Rill metrics views (see project docs for the known gap)
- Requires CUDA for 4-bit inference (bnb); CPU/MPS needs a different base model
- Library
- peft
- License
- apache-2.0
- Languages
- en
- Created
- Jun 23, 2026
- Updated
- Jun 23, 2026