Instructions to use HeliosFenrir/radiator-assistant-en with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HeliosFenrir/radiator-assistant-en with Transformers:

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

pipe = pipeline("text-generation", model="HeliosFenrir/radiator-assistant-en")
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("HeliosFenrir/radiator-assistant-en")
model = AutoModelForCausalLM.from_pretrained("HeliosFenrir/radiator-assistant-en", 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 HeliosFenrir/radiator-assistant-en with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/HeliosFenrir/radiator-assistant-en

SGLang

How to use HeliosFenrir/radiator-assistant-en 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 "HeliosFenrir/radiator-assistant-en" \
    --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": "HeliosFenrir/radiator-assistant-en",
		"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 "HeliosFenrir/radiator-assistant-en" \
        --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": "HeliosFenrir/radiator-assistant-en",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use HeliosFenrir/radiator-assistant-en with Docker Model Runner:
```
docker model run hf.co/HeliosFenrir/radiator-assistant-en
```

Radiator Assistant

Fine-tuned from Qwen/Qwen2.5-0.5B-Instruct for radiator replacement work (EN 442 / DIN 18380-style practice): procedures, inspection checklists, and material lists.

LoRA: HeliosFenrir/radiator-assistant-en-lora
Dataset: HeliosFenrir/radiator-en-sft

Not a substitute for manufacturer instructions, local codes, or a licensed installer. Prefer a structured parts list for BOMs; this model is best for procedures and inspection narrative.

Metrics

Metric	Value
Train / val	1200 / 120
Epochs	1
Eval loss	~0.038

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "HeliosFenrir/radiator-assistant-en"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(repo)

License

Derived from Qwen2.5-0.5B-Instruct (Apache-2.0).

Downloads last month: 103

Safetensors

Model size

0.5B params

Tensor type

F32

Model tree for HeliosFenrir/radiator-assistant-en

Base model

Qwen/Qwen2.5-0.5B

Finetuned

Qwen/Qwen2.5-0.5B-Instruct

Finetuned

(1165)

this model