Instructions to use Skywork/Skywork-R1V2-38B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Skywork/Skywork-R1V2-38B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="Skywork/Skywork-R1V2-38B")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Skywork/Skywork-R1V2-38B", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Skywork/Skywork-R1V2-38B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Skywork/Skywork-R1V2-38B" # 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-R1V2-38B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Skywork/Skywork-R1V2-38B
- SGLang
How to use Skywork/Skywork-R1V2-38B 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-R1V2-38B" \ --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-R1V2-38B", "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-R1V2-38B" \ --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-R1V2-38B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Skywork/Skywork-R1V2-38B with Docker Model Runner:
docker model run hf.co/Skywork/Skywork-R1V2-38B
Update README.md
Browse files
README.md
CHANGED
|
@@ -29,26 +29,48 @@ license: mit
|
|
| 29 |
## 2. Evaluation
|
| 30 |
|
| 31 |
|
| 32 |
-
<
|
| 33 |
-
|
| 34 |
-
|
| 35 |
-
|
| 36 |
-
|
| 37 |
-
|
| 38 |
-
|
| 39 |
-
|
| 40 |
-
|
| 41 |
-
|
| 42 |
-
|
| 43 |
-
|
| 44 |
-
|
| 45 |
-
|
| 46 |
-
|
| 47 |
-
|
| 48 |
-
|
| 49 |
-
|
| 50 |
-
|
| 51 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
<table>
|
| 53 |
<thead>
|
| 54 |
<tr>
|
|
@@ -248,10 +270,8 @@ license: mit
|
|
| 248 |
</tr>
|
| 249 |
</tbody>
|
| 250 |
</table>
|
| 251 |
-
<
|
| 252 |
-
|
| 253 |
-
</div>
|
| 254 |
-
<br>
|
| 255 |
|
| 256 |
|
| 257 |
|
|
|
|
| 29 |
## 2. Evaluation
|
| 30 |
|
| 31 |
|
| 32 |
+
<style>
|
| 33 |
+
section {
|
| 34 |
+
margin-bottom: 4em;
|
| 35 |
+
}
|
| 36 |
+
figure {
|
| 37 |
+
margin: 2em 0;
|
| 38 |
+
text-align: center;
|
| 39 |
+
}
|
| 40 |
+
figcaption {
|
| 41 |
+
font-weight: bold;
|
| 42 |
+
margin-top: 0.5em;
|
| 43 |
+
}
|
| 44 |
+
table {
|
| 45 |
+
margin: 3em auto;
|
| 46 |
+
width: 100%;
|
| 47 |
+
border-collapse: collapse;
|
| 48 |
+
}
|
| 49 |
+
table th, table td {
|
| 50 |
+
padding: 0.6em;
|
| 51 |
+
border: 1px solid #ddd;
|
| 52 |
+
text-align: center;
|
| 53 |
+
}
|
| 54 |
+
</style>
|
| 55 |
+
|
| 56 |
+
<section>
|
| 57 |
+
<figure>
|
| 58 |
+
<img src="open_source.png" alt="Open Source" width="100%" />
|
| 59 |
+
<figcaption>Comparison with Larger-Scale Open-Source Models</figcaption>
|
| 60 |
+
</figure>
|
| 61 |
+
</section>
|
| 62 |
+
|
| 63 |
+
<section>
|
| 64 |
+
<figure>
|
| 65 |
+
<img src="properitary.png" alt="Proprietary" width="100%" />
|
| 66 |
+
<figcaption>Comparison with Proprietary Models</figcaption>
|
| 67 |
+
</figure>
|
| 68 |
+
</section>
|
| 69 |
+
|
| 70 |
+
<section>
|
| 71 |
+
<div align="center">
|
| 72 |
+
<h3>Evaluation Results of State-of-the-Art LLMs and VLMs</h3>
|
| 73 |
+
</div>
|
| 74 |
<table>
|
| 75 |
<thead>
|
| 76 |
<tr>
|
|
|
|
| 270 |
</tr>
|
| 271 |
</tbody>
|
| 272 |
</table>
|
| 273 |
+
</section>
|
| 274 |
+
|
|
|
|
|
|
|
| 275 |
|
| 276 |
|
| 277 |
|