Instructions to use ducklingcodehouse/Finnish-DentalQA-merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ducklingcodehouse/Finnish-DentalQA-merged with Transformers:

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

pipe = pipeline("text-generation", model="ducklingcodehouse/Finnish-DentalQA-merged")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ducklingcodehouse/Finnish-DentalQA-merged")
model = AutoModelForCausalLM.from_pretrained("ducklingcodehouse/Finnish-DentalQA-merged", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ducklingcodehouse/Finnish-DentalQA-merged with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ducklingcodehouse/Finnish-DentalQA-merged

SGLang

How to use ducklingcodehouse/Finnish-DentalQA-merged 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 "ducklingcodehouse/Finnish-DentalQA-merged" \
    --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": "ducklingcodehouse/Finnish-DentalQA-merged",
		"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 "ducklingcodehouse/Finnish-DentalQA-merged" \
        --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": "ducklingcodehouse/Finnish-DentalQA-merged",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use ducklingcodehouse/Finnish-DentalQA-merged with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ducklingcodehouse/Finnish-DentalQA-merged to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ducklingcodehouse/Finnish-DentalQA-merged to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ducklingcodehouse/Finnish-DentalQA-merged to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="ducklingcodehouse/Finnish-DentalQA-merged",
    max_seq_length=2048,
)

Docker Model Runner
How to use ducklingcodehouse/Finnish-DentalQA-merged with Docker Model Runner:
```
docker model run hf.co/ducklingcodehouse/Finnish-DentalQA-merged
```

ducklingcodehouse commited on Sep 3, 2025

Commit

743a435

verified ·

1 Parent(s): 8484e81

Update model card

Browse files

Files changed (1) hide show

README.md +11 -3

README.md CHANGED Viewed

@@ -30,6 +30,8 @@ base_model: Finnish-NLP/Ahma-3B-Instruct
 LoRA fine-tuned model merged into standalone format for Finnish dental medicine consultations between healthcare professionals. Trained on 30,908 synthetic dental conversations (80% expert clinical cases, 20% concept explanations) covering a broad range of different scenarios. Generated using pipeline with GPT-4.1.
 **Research Focus:** This model demonstrates domain-specific fine-tuning with low computational resources. The goal is to explore how specialized models can be trained and deployed on consumer hardware (including personal GPUs) rather than requiring high-end infrastructure.
 **System prompt recommendation:** This model was trained with a specific system prompt. For best results, we recommend using the same prompt format shown in the examples below.
@@ -44,9 +46,13 @@ This llama model was trained 2x faster with [Unsloth](https://github.com/unsloth
 ## Model Comparison
-**Merged Version**: LoRA adapters merged into standalone model, no additional files needed
-**LoRA Version**: Separate adapter files, requires base model
 ## Installation
@@ -200,7 +206,9 @@ Potilas tulee lähettää välittömästi päivystykseen sairaalatasolle suonens
 - Potential underrepresentation of certain patient demographics or clinical scenarios
 ## Related Models
-- LoRA version: [ducklingcodehouse/Finnish-DentalQA-lora](https://huggingface.co/ducklingcodehouse/Finnish-DentalQA-lora)
 - Base model: [Finnish-NLP/Ahma-3B-Instruct](https://huggingface.co/Finnish-NLP/Ahma-3B-Instruct)
 ## Citation

 LoRA fine-tuned model merged into standalone format for Finnish dental medicine consultations between healthcare professionals. Trained on 30,908 synthetic dental conversations (80% expert clinical cases, 20% concept explanations) covering a broad range of different scenarios. Generated using pipeline with GPT-4.1.
+**Note:** Version 2 models are now available with enhanced training datasets (50,132 conversations) and improved clinical coverage including psychological, social, and ethical aspects. See [Finnish-DentalQA-v2-lora](https://huggingface.co/ducklingcodehouse/Finnish-DentalQA-v2-lora) and [Finnish-DentalQA-v2-merged](https://huggingface.co/ducklingcodehouse/Finnish-DentalQA-v2-merged).
 **Research Focus:** This model demonstrates domain-specific fine-tuning with low computational resources. The goal is to explore how specialized models can be trained and deployed on consumer hardware (including personal GPUs) rather than requiring high-end infrastructure.
 **System prompt recommendation:** This model was trained with a specific system prompt. For best results, we recommend using the same prompt format shown in the examples below.
 ## Model Comparison
+**v1 LoRA Version**: [ducklingcodehouse/Finnish-DentalQA-lora](https://huggingface.co/ducklingcodehouse/Finnish-DentalQA-lora) - Separate adapter files, requires base model
+**v1 Merged Version**: LoRA adapters merged into standalone model, no additional files needed
+**v2 LoRA Version**: [ducklingcodehouse/Finnish-DentalQA-v2-lora](https://huggingface.co/ducklingcodehouse/Finnish-DentalQA-v2-lora) - Enhanced training (50,132 samples vs 30,908), improved clinical coverage, separate adapter files, requires base model
+**v2 Merged Version**: [ducklingcodehouse/Finnish-DentalQA-v2-merged](https://huggingface.co/ducklingcodehouse/Finnish-DentalQA-v2-merged) - Enhanced training (50,132 samples vs 30,908), improved clinical coverage, LoRA adapters merged into standalone model
 ## Installation
 - Potential underrepresentation of certain patient demographics or clinical scenarios
 ## Related Models
+- v1 LoRA version: [ducklingcodehouse/Finnish-DentalQA-lora](https://huggingface.co/ducklingcodehouse/Finnish-DentalQA-lora)
+- v2 LoRA version: [ducklingcodehouse/Finnish-DentalQA-v2-lora](https://huggingface.co/ducklingcodehouse/Finnish-DentalQA-v2-lora)
+- v2 Merged version: [ducklingcodehouse/Finnish-DentalQA-v2-merged](https://huggingface.co/ducklingcodehouse/Finnish-DentalQA-v2-merged)
 - Base model: [Finnish-NLP/Ahma-3B-Instruct](https://huggingface.co/Finnish-NLP/Ahma-3B-Instruct)
 ## Citation