Update README.md
Browse files
README.md
CHANGED
@@ -322,6 +322,21 @@ code_embeddings = model.encode(
|
|
322 |
```
|
323 |
</details>
|
324 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
325 |
|
326 |
## Jina-VDR
|
327 |
Alongside `jina-embeddings-v4`, we’re releasing [Jina VDR](https://github.com/jina-ai/jina-vdr), a multilingual, multi-domain benchmark for visual document retrieval. The task collection can be viewed [here](https://huggingface.co/collections/jinaai/jinavdr-visual-document-retrieval-684831c022c53b21c313b449), and evaluation instructions can be found [here](https://github.com/jina-ai/jina-vdr).
|
|
|
322 |
```
|
323 |
</details>
|
324 |
|
325 |
+
<details>
|
326 |
+
<summary>via <a href="https://github.com/vllm-project/vllm">vLLM</a></summary>
|
327 |
+
|
328 |
+
We provide separate model versions for each task (`retrieval`, `text-matching`, `code`) where specific adapter is merged into the base `Qwen2.5-VL` weights.
|
329 |
+
This modification enables native compatibility with vLLM.
|
330 |
+
|
331 |
+
Instructions and usage examples for each task are available in their respective directories:
|
332 |
+
- [jina-embeddings-v4-vllm-retrieval](https://huggingface.co/jinaai/jina-embeddings-v4-vllm-retrieval)
|
333 |
+
- [jina-embeddings-v4-vllm-text-matching](https://huggingface.co/jinaai/jina-embeddings-v4-vllm-text-matching)
|
334 |
+
- [jina-embeddings-v4-vllm-code](https://huggingface.co/jinaai/jina-embeddings-v4-vllm-code)
|
335 |
+
|
336 |
+
Please refer to the directory that matches your task for more details.
|
337 |
+
|
338 |
+
</details>
|
339 |
+
|
340 |
|
341 |
## Jina-VDR
|
342 |
Alongside `jina-embeddings-v4`, we’re releasing [Jina VDR](https://github.com/jina-ai/jina-vdr), a multilingual, multi-domain benchmark for visual document retrieval. The task collection can be viewed [here](https://huggingface.co/collections/jinaai/jinavdr-visual-document-retrieval-684831c022c53b21c313b449), and evaluation instructions can be found [here](https://github.com/jina-ai/jina-vdr).
|