Instructions to use Ronin48LLC/bruno-lora-adapter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ronin48LLC/bruno-lora-adapter with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.3-70B-Instruct")
model = PeftModel.from_pretrained(base_model, "Ronin48LLC/bruno-lora-adapter")

Transformers

How to use Ronin48LLC/bruno-lora-adapter with Transformers:

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

pipe = pipeline("text-generation", model="Ronin48LLC/bruno-lora-adapter")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Ronin48LLC/bruno-lora-adapter", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Ronin48LLC/bruno-lora-adapter with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ronin48LLC/bruno-lora-adapter"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ronin48LLC/bruno-lora-adapter",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ronin48LLC/bruno-lora-adapter

SGLang

How to use Ronin48LLC/bruno-lora-adapter 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 "Ronin48LLC/bruno-lora-adapter" \
    --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": "Ronin48LLC/bruno-lora-adapter",
		"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 "Ronin48LLC/bruno-lora-adapter" \
        --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": "Ronin48LLC/bruno-lora-adapter",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Ronin48LLC/bruno-lora-adapter with Docker Model Runner:
```
docker model run hf.co/Ronin48LLC/bruno-lora-adapter
```

BRUNO — Building Rescue and Unified Navigation Operations

"There is no call too routine or too small to treat with complete respect." — Chief Alan Brunacini, Phoenix Fire Department

An open-source LoRA adapter for fire service tactical decision support.

BRUNO is a QLoRA adapter on top of Meta Llama 3.3 70B Instruct, fine-tuned on fire service operations, incident command, hazardous materials, structural firefighting tactics, and rescue operations — built to assist Firefighters, Company Officers, and Incident Commanders in the field and in training. Model #5 of the Ronin 48 first-responder suite, alongside BONES (EMS) and SELMA (law enforcement).

Model Details

Field	Value
Base Model	meta-llama/Llama-3.3-70B-Instruct
Adapter Type	LoRA (QLoRA)
LoRA Rank / Alpha / Dropout	64 / 128 / 0.05
Target Modules	`q_proj`, `k_proj`, `v_proj`, `o_proj`, `gate_proj`, `up_proj`, `down_proj`
Task	Fireground size-up, incident command, hazmat and rescue decision support
Training Method	QLoRA supervised fine-tuning via `SFTTrainer` (trl)
License	MIT (adapter weights)
Maintainer	Ronin48LLC

Capabilities

Size-up — building construction types, occupancy hazards, life-safety priorities, RECEO-VS
Incident Command — ICS/NIMS structure, sector assignments, resource tracking, span of control
Structural firefighting — attack-line placement, ventilation, search and rescue, RIT operations
Hazmat — DOT placard identification, ERG lookups, decon procedures, hot/warm/cold zones
Extrication — vehicle stabilization, disentanglement, tool selection, medical coordination
Water supply — hydrant calculations, relay pumping, tanker shuttle, rural water ops
Wildland/WUI — LCES, fire behavior, structure triage, defensible-space assessment
Special rescue — confined space, trench, rope, water
Mayday/RIT — LUNAR reporting, air management, thermal imaging, RIT deployment
Pre-fire planning — walkthrough checklists, Knox box, FDC locations, occupant load

Intended Use

For trained fire service personnel:

Tactical decision support in training scenarios and tabletop exercises
ICS structure and span-of-control reference
Hazmat identification and ERG reference
Mayday/RIT procedure review
NFPA code and IFSTA curriculum reference
After-action review and training development

BRUNO is a tactical decision support tool, not a replacement for your training, your officer, or your IC. When in doubt, call your IC.

Limitations

Read LIMITATIONS.md before deploying in any operational context. In short:

BRUNO is not an Incident Commander; it cannot replace the situational awareness, judgment, and authority of the officer on scene.
It does not know your building, your resources, or your SOGs — department guidelines always take precedence.
It cannot declare a Mayday. Only the member in distress or their officer does that.
Hazmat recommendations must be verified against the current ERG and your local hazmat team.
It has a training-data cutoff; NFPA editions, IFSTA updates, and new fire-behavior research may not be reflected.
It is not a substitute for NFPA compliance review by the authority having jurisdiction.

Usage

This is a PEFT LoRA adapter. Load it on top of the base model:

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base_model = AutoModelForCausalLM.from_pretrained(
    "meta-llama/Llama-3.3-70B-Instruct",
    load_in_4bit=True,
    device_map="auto",
)
model = PeftModel.from_pretrained(base_model, "Ronin48LLC/bruno-lora-adapter")
tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.3-70B-Instruct")

Note: Access to the base model requires accepting Meta's license on Hugging Face.

The base model with the BRUNO system prompt and no fine-tuning is a workable baseline; see the source repository's Quick Start.

Training

Framework: PyTorch + Transformers + TRL + PEFT, 4-bit quantized base
Adapter config: rank 64, alpha 128, dropout 0.05, all seven attention and MLP projections (see adapter_config.json)
Run details: training_args.bin is preserved in this repository; the step count and loss curve were not recorded in the upload

Training Data Sources

Source	Description	License
NFPA 1 / NFPA 101 / NFPA 13	Fire code, life safety, suppression systems	Public reference
IFSTA Essentials / Fire Officer	Core firefighter and officer curriculum	Public guidelines
NIOSH Fire Fighter Fatality Reports	Line-of-duty death investigations	Public Domain
NIST Fire Research	Structural fire behavior research, UL studies	Public Domain
DOT Emergency Response Guidebook	Hazardous materials emergency response	Public Domain
ICS-100 through ICS-400	FEMA NIMS/ICS training materials	Public Domain
FEMA/USFA Fire Data	National fire statistics, incident data	Public Domain
Synthetic Scenarios	AI-generated fireground and incident scenarios	Proprietary

Related Models — the Ronin 48 first-responder suite

BRUNO, BONES, and SELMA share scenes constantly — consult the appropriate model for each domain.

Model	Domain	Use when…
BRUNO (this adapter)	Fire service — company officer / IC	Fireground tactics, size-up, hazmat, extrication, water supply, ICS
BONES	EMS — EMR / EMT / AEMT / Paramedic	Patient assessment, treatment protocols, drug dosing, triage, transport
SELMA	Law enforcement	Criminal statute identification, charge elements, constitutional flags

Shared scene	Primary	Support
Structure fire with casualties	BRUNO (fireground ops)	BONES (patient care)
Vehicle accident with entrapment	BRUNO (extrication)	BONES (care during extrication)
Hazmat with patient exposures	BRUNO (mitigation, decon zone)	BONES (patient decon and treatment)
Mass casualty incident	BONES (triage, treatment)	BRUNO (ICS, sectors) + SELMA (criminal nexus)
Arson investigation	BRUNO (origin/cause, fire behavior)	SELMA (arson statutes) + BONES (patient care)
Wildland/WUI with structure threat	BRUNO (tactical operations)	BONES (civilian casualties)
Confined-space rescue	BRUNO (rescue ops, atmospheric monitoring)	BONES (patient extraction and care)

ABBY (forensics) operates independently of the first-responder suite; SELMA pairs with ATTICUS on the legal side.

Source

github.com/CryptoJones/BRUNO — data collection, QLoRA pipeline, synthetic-scenario generator.

License

Downloads last month: 17

Model tree for Ronin48LLC/bruno-lora-adapter

Base model

meta-llama/Llama-3.1-70B

Finetuned

meta-llama/Llama-3.3-70B-Instruct

Adapter

(443)

this model