Instructions to use user55442/Vilnius-Bus-Stop-LLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use user55442/Vilnius-Bus-Stop-LLM with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/Qwen3-VL-2B-Instruct")
model = PeftModel.from_pretrained(base_model, "user55442/Vilnius-Bus-Stop-LLM")

Transformers

How to use user55442/Vilnius-Bus-Stop-LLM with Transformers:

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

pipe = pipeline("text-generation", model="user55442/Vilnius-Bus-Stop-LLM")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("user55442/Vilnius-Bus-Stop-LLM", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use user55442/Vilnius-Bus-Stop-LLM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "user55442/Vilnius-Bus-Stop-LLM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "user55442/Vilnius-Bus-Stop-LLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/user55442/Vilnius-Bus-Stop-LLM

SGLang

How to use user55442/Vilnius-Bus-Stop-LLM 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 "user55442/Vilnius-Bus-Stop-LLM" \
    --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": "user55442/Vilnius-Bus-Stop-LLM",
		"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 "user55442/Vilnius-Bus-Stop-LLM" \
        --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": "user55442/Vilnius-Bus-Stop-LLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use user55442/Vilnius-Bus-Stop-LLM 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 user55442/Vilnius-Bus-Stop-LLM 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 user55442/Vilnius-Bus-Stop-LLM to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for user55442/Vilnius-Bus-Stop-LLM to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="user55442/Vilnius-Bus-Stop-LLM",
    max_seq_length=2048,
)

Docker Model Runner
How to use user55442/Vilnius-Bus-Stop-LLM with Docker Model Runner:
```
docker model run hf.co/user55442/Vilnius-Bus-Stop-LLM
```

Vilnius-Bus-Stop-LLM / README.md

user55442

Update README.md

a9187dc verified about 1 month ago

preview code

Raw

History Blame Contribute Delete

2.8 kB

	---
	base_model: unsloth/Qwen3-VL-2B-Instruct
	library_name: peft
	pipeline_tag: text-generation
	tags:
	- base_model:adapter:unsloth/Qwen3-VL-2B-Instruct
	- lora
	- sft
	- transformers
	- trl
	- unsloth
	- lithuanian
	- vision-language
	- bus-stop
	language:
	- lt
	license: apache-2.0
	---

	# Vilnius Bus Stop LLM

	A LoRA adapter fine-tuned on [Qwen3-VL-2B-Instruct](https://huggingface.co/unsloth/Qwen3-VL-2B-Instruct) to recognize Vilnius bus stops in images and describe them in Lithuanian.

	## Model Details

	- Model type: Vision-Language Model (LoRA adapter)
	- Base model: `unsloth/Qwen3-VL-2B-Instruct`
	- Language: Lithuanian (lt)
	- Fine-tuning framework: [Unsloth](https://github.com/unslothai/unsloth)
	- Task: Image captioning of bus stops in Lithuanian

	## How to Get Started

	```python
	from peft import PeftModel
	from transformers import AutoProcessor, Qwen2VLForConditionalGeneration
	import torch

	base_model = "unsloth/Qwen3-VL-2B-Instruct"
	adapter = "user55442/Vilnius-Bus-Stop-LLM"

	model = Qwen2VLForConditionalGeneration.from_pretrained(
	base_model,
	torch_dtype=torch.bfloat16,
	device_map="auto",
	ignore_mismatched_sizes=True
	)
	model = PeftModel.from_pretrained(model, adapter)
	processor = AutoProcessor.from_pretrained(base_model)

	```

	## Training Details

	### Dataset
	- 150 daytime images of Vilnius bus stops, captured from varying angles and distances
	- Captions generated in English by Gemini, then translated to Lithuanian
	- 80/20 train/eval split → 120 training images, 30 test images

	### Training Procedure
	- Epochs: 8 (optimal checkpoint ~step 120 before overfitting)
	- Batch size: 1 with gradient accumulation over 4 steps
	- Learning rate: 1e-4 (AdamW 8-bit optimizer)
	- Precision: bfloat16
	- Image resolution: max 768×768
	- LoRA target layers: language and attention layers (vision layers frozen)

	## Evaluation Results

	### Intrinsic Metrics

	\| Metric \| Base \| Fine-tuned \|
	\|---\|---\|---\|
	\| ROUGE-L \| 0.014 \| 0.163 \|
	\| Semantic Similarity \| 0.731 \| 0.801 \|
	\| BLEU \| 0.339 \| 10.130 \|
	\| BERTScore F1 \| 0.811 \| 0.864 \|
	\| Perplexity \| 14.170 \| 6544.885 \|

	### LLM Judge Scores (Gemma-4-31B, scale 1–10)

	\| Metric \| Base \| Fine-tuned \|
	\|---\|---\|---\|
	\| Fluency \| 9.77 \| 5.67 \|
	\| Relevance \| 8.47 \| 6.37 \|
	\| Factual Accuracy \| 7.60 \| 5.20 \|
	\| Creativity \| 8.80 \| 5.40 \|

	## Limitations

	- Trained on only 120 images — model shows signs of overfitting after ~120 steps
	- Perplexity increased sharply (14 → 6544), suggesting the model partially overfit to caption style
	- LLM judge noted grammatical errors, hallucinations, and incomplete sentences in some outputs
	- Performance may degrade on bus stops outside Vilnius or in different lighting conditions

	## Framework Versions

	- PEFT 0.19.1
	- Unsloth
	- Transformers