Instructions to use Irfanuruchi/OLMo-2-1124-7B-BuildEng with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Irfanuruchi/OLMo-2-1124-7B-BuildEng with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Irfanuruchi/OLMo-2-1124-7B-BuildEng")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Irfanuruchi/OLMo-2-1124-7B-BuildEng")
model = AutoModelForCausalLM.from_pretrained("Irfanuruchi/OLMo-2-1124-7B-BuildEng", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Irfanuruchi/OLMo-2-1124-7B-BuildEng with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Irfanuruchi/OLMo-2-1124-7B-BuildEng"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Irfanuruchi/OLMo-2-1124-7B-BuildEng",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Irfanuruchi/OLMo-2-1124-7B-BuildEng

SGLang

How to use Irfanuruchi/OLMo-2-1124-7B-BuildEng with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Irfanuruchi/OLMo-2-1124-7B-BuildEng" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Irfanuruchi/OLMo-2-1124-7B-BuildEng",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Irfanuruchi/OLMo-2-1124-7B-BuildEng" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Irfanuruchi/OLMo-2-1124-7B-BuildEng",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Irfanuruchi/OLMo-2-1124-7B-BuildEng with Docker Model Runner:
```
docker model run hf.co/Irfanuruchi/OLMo-2-1124-7B-BuildEng
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

OLMo-2-1124-7B-BuildEng

OLMo-2-1124-7B-BuildEng is a 7B parameter OLMo 2 derivative fine-tuned for building engineering.

The training work focuses on structural diagnostics, reinforced concrete, foundations and geotechnics, building physics, construction materials, HVAC and building services, durability, construction sequencing, site investigation, and conservative engineering judgment.

The base model is allenai/OLMo-2-1124-7B-Instruct.

Training

The model was trained with NF4 QLoRA and the selected adapter was merged back into the native BF16 base model for this release.

LoRA rank: 16
LoRA alpha: 32
LoRA dropout: 0.05
Selected checkpoint: update 2816
Training split: 48,495 rows
Rows consumed by the frozen production schedule: 48,480
Training hardware: AMD Radeon RX 9060 XT 16 GB
Runtime: ROCm

The public BuildEng repository is larger than the frozen split used for this experiment. Linking the dataset here should not be read as saying that every current public row was used during this training run.

Evaluation

A post-training quantization-retention check used 16 Building Engineering prompts and five representations of the same fine-tuned model:

Format	Aggregate score	Mean / 20
Q5_K_M	182 / 320	11.375
Q8_0	180 / 320	11.250
Q6_K	178 / 320	11.125
BF16	171 / 320	10.688
Q4_K_M	162 / 320	10.125

Model identities were hidden from the evaluator until all 80 scores had been completed and frozen.

Q5_K_M had the highest observed aggregate score in this suite. This is not evidence that quantization improves the model. The overall difference between the five representations was not statistically significant in this small evaluation (Friedman test, p = 0.231).

The generation limit was 512 tokens. The evaluator noted truncation or abrupt cutoff in 65 of 80 responses, so these absolute scores should not be treated as a complete measure of the model's Building Engineering capability.

One challenge prompt overlapped in scenario with an earlier ad-hoc prompt concept and is therefore not used for a strict fresh-prompt claim. Excluding that prompt leaves the observed ordering unchanged.

No comparison against the untouched base OLMo 2 model was performed in this qualification stage.

The training dataset also contains recurring answer and template strings. Very low held-out language-model loss should therefore not be interpreted as evidence of universal engineering reasoning.

Intended use

This model is intended for research, education, technical drafting, local inference, and experiments with building-engineering assistants.

It is not a substitute for a licensed engineer, project-specific calculations, site investigation, code compliance review, or professional judgment.

Engineering recommendations should be checked against the applicable codes, project documents, material data, site conditions, and qualified professional review.

GGUF

GGUF files are published separately:

Irfanuruchi/OLMo-2-1124-7B-BuildEng-GGUF

Dataset

BuildEng:

Irfanuruchi/buildeng

License and upstream work

This repository is released under Apache-2.0.

OLMo 2 was developed by the Allen Institute for AI. Users should also review the upstream OLMo 2 model card, Responsible Use Guidelines, and the additional upstream terms referenced by that model card.