license: other
license_name: qwen-research
license_link: https://huggingface.co/Qwen/Qwen2.5-3B-Instruct/blob/main/LICENSE
language:
- en
library_name: openvino
pipeline_tag: text-generation
base_model: Irfanuruchi/qwen2.5-3b-buildeng
datasets:
- Irfanuruchi/buildeng-v8-3b
tags:
- openvino
- qwen2
- civil-engineering
- structural-engineering
- building-engineering
- construction
- text-generation
- conversational
- engineering
BuildEng V8 3B — OpenVINO FP16
BuildEng V8 3B OpenVINO FP16 is the higher-precision OpenVINO release of BuildEng V8 3B, a domain-specialized language model focused on civil engineering, structural reasoning, construction workflows, and conservative engineering-assistant behavior.
This release is converted from:
Irfanuruchi/qwen2.5-3b-buildeng
The BuildEng V8 3B model is fine-tuned from:
Qwen/Qwen2.5-3B-Instruct
Improved using Qwen.
Model Information
| Property | Value |
|---|---|
| Model | BuildEng V8 3B |
| Runtime | OpenVINO |
| Precision | FP16 |
| BuildEng source model | Irfanuruchi/qwen2.5-3b-buildeng |
| Upstream model | Qwen/Qwen2.5-3B-Instruct |
| Domain | Civil and structural engineering |
| Primary use | Intel-optimized local engineering-assistant inference |
This FP16 release is intended for users who prioritize model precision and output quality over reduced storage or memory requirements.
Focus Areas
BuildEng is designed around engineering and construction workflows including:
- reinforced concrete
- masonry
- foundations and settlement
- retaining walls
- slabs, beams, and columns
- building defects and pathology
- structural diagnostics
- renovation and existing-structure uncertainty
- structural inspection guidance
- temporary works
- construction sequencing
- inspection-first reasoning
- conservative engineering recommendations
The model is designed to function as an engineering assistant and to avoid presenting uncertain conclusions as established facts.
Why This Version?
The OpenVINO FP16 release is intended to provide:
- higher precision than compressed BuildEng OpenVINO releases
- strong output quality for local inference
- efficient deployment through the OpenVINO runtime
- a practical option for capable Intel-based systems
- compatibility with CPU and other OpenVINO-supported accelerators where available
A 3B INT4 OpenVINO export was evaluated during development but was not published because its output was not sufficiently stable for release.
Installation
pip install "optimum-intel[openvino]" openvino transformers
Usage
from optimum.intel.openvino import OVModelForCausalLM
from transformers import AutoTokenizer
model_id = "Irfanuruchi/qwen2.5-3b-buildeng-openvino-fp16"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = OVModelForCausalLM.from_pretrained(
model_id,
device="CPU",
compile=True,
)
messages = [
{
"role": "system",
"content": (
"You are BuildEng. Give concise, inspection-first "
"building engineering guidance."
),
},
{
"role": "user",
"content": (
"A homeowner reports diagonal cracks near a window corner. "
"What should be inspected first?"
),
},
]
prompt = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True,
)
inputs = tokenizer(prompt, return_tensors="pt")
output = model.generate(
**inputs,
max_new_tokens=160,
do_sample=False,
)
new_tokens = output[0][inputs["input_ids"].shape[-1]:]
print(tokenizer.decode(new_tokens, skip_special_tokens=True))
Devices
Depending on the OpenVINO installation, hardware, and platform support, this release may be used with:
- CPU
- GPU
- NPU where supported
BuildEng Model Family
Merged 3B Model
Irfanuruchi/qwen2.5-3b-buildeng
Other Formats
| Format | Repository |
|---|---|
| Hugging Face | Irfanuruchi/qwen2.5-3b-buildeng |
| GGUF Q4_K_M | Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q4_K_M |
| GGUF Q8_0 | Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q8_0 |
| GGUF F16 | Irfanuruchi/qwen2.5-3b-buildeng-GGUF-F16 |
| MLX 4-bit | Irfanuruchi/qwen2.5-3b-buildeng-mlx-4bit |
| MLX 8-bit | Irfanuruchi/qwen2.5-3b-buildeng-mlx-8bit |
| OpenVINO INT8 | Irfanuruchi/qwen2.5-3b-buildeng-openvino-int8 |
Training Dataset
Irfanuruchi/buildeng-v8-3b
License and Commercial Use
BuildEng V8 3B is derived from Qwen/Qwen2.5-3B-Instruct. The upstream Qwen2.5-3B-Instruct model is distributed under the Qwen Research License Agreement, and the applicable upstream licensing terms continue to apply to this OpenVINO derivative release.
Under the upstream Qwen Research License Agreement, the default grant of rights to use, reproduce, distribute, modify, and create derivative works from the Qwen materials is limited to non-commercial research and evaluation purposes.
Commercial use of the upstream Qwen materials requires requesting the appropriate license from Alibaba Cloud.
Accordingly, Apache-2.0 licensing applicable to other BuildEng model families must not be interpreted as granting Apache-2.0 rights over the upstream Qwen2.5-3B materials contained in this release.
A copy of the upstream Qwen Research License Agreement is included in this repository as:
LICENSE
The required Qwen attribution and BuildEng modification information are included in:
NOTICE
Qwen Attribution
Qwen is licensed under the Qwen RESEARCH LICENSE AGREEMENT, Copyright (c) Alibaba Cloud. All Rights Reserved.
Improved using Qwen.
Commercial BuildEng Alternatives
For applications that require a BuildEng model based on an upstream Apache-2.0-licensed model, BuildEng variants based on Qwen2.5-1.5B and Qwen2.5-32B are available separately.
Users are responsible for reviewing and complying with all licenses applicable to their intended use and deployment.
Engineering Use Notice
BuildEng is an engineering-assistant model and is not a substitute for professional engineering judgment.
Model output should not be treated as:
- final structural approval
- construction authorization
- engineering certification or sign-off
- a substitute for calculations required by applicable codes or standards
- a substitute for inspection of actual site conditions
- a replacement for review by a qualified or licensed engineer where required
Engineering decisions should be independently verified using appropriate calculations, standards, drawings, site information, project-specific constraints, and professional review.
Modifications and Model Lineage
This repository contains an OpenVINO FP16 conversion of the fine-tuned BuildEng V8 3B model.
Model lineage:
Qwen/Qwen2.5-3B-Instruct
→ Irfanuruchi/qwen2.5-3b-buildeng
→ Irfanuruchi/qwen2.5-3b-buildeng-openvino-fp16
BuildEng-specific model development, fine-tuning, engineering specialization, documentation, and related project contributions were produced by Irfan Uruçi.
The OpenVINO FP16 conversion represented by this repository is a modified/converted derivative of the BuildEng V8 3B release.
Upstream Qwen intellectual-property rights remain subject to the Qwen Research License Agreement.
Author
Irfan Uruçi BuildEng Project