Instructions to use merve/smol-vision with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use merve/smol-vision with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="merve/smol-vision")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("merve/smol-vision", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use merve/smol-vision with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "merve/smol-vision" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "merve/smol-vision", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/merve/smol-vision
- SGLang
How to use merve/smol-vision 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 "merve/smol-vision" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "merve/smol-vision", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "merve/smol-vision" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "merve/smol-vision", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use merve/smol-vision with Docker Model Runner:
docker model run hf.co/merve/smol-vision
Update README.md
Browse files
README.md
CHANGED
|
@@ -12,6 +12,7 @@ Latest examples 👇🏻
|
|
| 12 |
- [Fine-tune ColPali for Multimodal RAG](https://huggingface.co/merve/smol-vision/blob/main/Finetune_ColPali.ipynb)
|
| 13 |
- [Fine-tune Gemma-3n for all modalities (audio-text-image)](https://huggingface.co/merve/smol-vision/blob/main/Gemma3n_Fine_tuning_on_All_Modalities.ipynb)
|
| 14 |
- [Any-to-Any (Video) RAG with OmniEmbed and Qwen](https://huggingface.co/merve/smol-vision/blob/main/Any_to_Any_RAG.ipynb)
|
|
|
|
| 15 |
**Note**: The script and notebook are updated to fix few issues related to QLoRA!
|
| 16 |
|
| 17 |
| | Notebook | Description |
|
|
|
|
| 12 |
- [Fine-tune ColPali for Multimodal RAG](https://huggingface.co/merve/smol-vision/blob/main/Finetune_ColPali.ipynb)
|
| 13 |
- [Fine-tune Gemma-3n for all modalities (audio-text-image)](https://huggingface.co/merve/smol-vision/blob/main/Gemma3n_Fine_tuning_on_All_Modalities.ipynb)
|
| 14 |
- [Any-to-Any (Video) RAG with OmniEmbed and Qwen](https://huggingface.co/merve/smol-vision/blob/main/Any_to_Any_RAG.ipynb)
|
| 15 |
+
|
| 16 |
**Note**: The script and notebook are updated to fix few issues related to QLoRA!
|
| 17 |
|
| 18 |
| | Notebook | Description |
|