Instructions to use drwlf/Claria-14b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use drwlf/Claria-14b with Transformers:

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

pipe = pipeline("text-generation", model="drwlf/Claria-14b")
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("drwlf/Claria-14b")
model = AutoModelForCausalLM.from_pretrained("drwlf/Claria-14b", 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 drwlf/Claria-14b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "drwlf/Claria-14b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "drwlf/Claria-14b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/drwlf/Claria-14b

SGLang

How to use drwlf/Claria-14b 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 "drwlf/Claria-14b" \
    --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": "drwlf/Claria-14b",
		"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 "drwlf/Claria-14b" \
        --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": "drwlf/Claria-14b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use drwlf/Claria-14b with Docker Model Runner:
```
docker model run hf.co/drwlf/Claria-14b
```

Claria 8B

by BRP - opened May 29, 2025

Discussion

BRP

May 29, 2025

Dear Dr. Alexandru Lupoi,

If possible, can you please add also an 8B version of Claria to your Models Collection in GGUF format?

Thank you for your attention!

Best Regards,
BRP

drwlf

Owner May 29, 2025

Yes, I’ll finished an updated training and upload the new model and gguf’s for it! In the meantime feel free to check out the medical model, Medra 😁

BRP

May 29, 2025

Thank you so much! And congratulations on the Claria model, it's fantastic. I will certainly also like a lot the medical model, Medra, that you mentioned. 😁

Thanks again! And all the best!

drwlf

Owner May 29, 2025

That one is more advanced, even outputting reasoning if you use the system prompt, which is unusal for Gemma 3 based models. It will begin vision training on a variety of vision datasets soon

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment