Instructions to use Skywork/Skywork-R1V-38B-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Skywork/Skywork-R1V-38B-AWQ with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="Skywork/Skywork-R1V-38B-AWQ")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Skywork/Skywork-R1V-38B-AWQ", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Skywork/Skywork-R1V-38B-AWQ with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Skywork/Skywork-R1V-38B-AWQ" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Skywork/Skywork-R1V-38B-AWQ", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Skywork/Skywork-R1V-38B-AWQ
- SGLang
How to use Skywork/Skywork-R1V-38B-AWQ 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 "Skywork/Skywork-R1V-38B-AWQ" \ --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": "Skywork/Skywork-R1V-38B-AWQ", "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 "Skywork/Skywork-R1V-38B-AWQ" \ --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": "Skywork/Skywork-R1V-38B-AWQ", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Skywork/Skywork-R1V-38B-AWQ with Docker Model Runner:
docker model run hf.co/Skywork/Skywork-R1V-38B-AWQ
Add metadata: pipeline tag, library name, and license
Browse filesThis PR adds the missing metadata to the model card, including `pipeline_tag`, `library_name`, and `license`. The `pipeline_tag` is set to `image-text-to-text` based on the model's multimodal capabilities.
README.md
CHANGED
|
@@ -1,3 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# Skywork-R1V-38B-AWQ
|
| 2 |
|
| 3 |
<div align="center">
|
|
@@ -257,4 +263,5 @@ print(response.text)
|
|
| 257 |
archivePrefix={arXiv},
|
| 258 |
primaryClass={cs.CV},
|
| 259 |
url={https://arxiv.org/abs/2504.05599},
|
| 260 |
-
}
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
library_name: transformers
|
| 4 |
+
pipeline_tag: image-text-to-text
|
| 5 |
+
---
|
| 6 |
+
|
| 7 |
# Skywork-R1V-38B-AWQ
|
| 8 |
|
| 9 |
<div align="center">
|
|
|
|
| 263 |
archivePrefix={arXiv},
|
| 264 |
primaryClass={cs.CV},
|
| 265 |
url={https://arxiv.org/abs/2504.05599},
|
| 266 |
+
}
|
| 267 |
+
```
|