Issue Station
Sign In
Tools hereToolbox

vllm - ✅(Solved) Fix [New Model]: JinaEmbeddingsV5Model [1 pull requests, 2 comments, 2 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
vllm-project/vllm#38633•Fetched 2026-04-08 01:58:52
View on GitHub
Comments
2
Participants
2
Timeline
5
Reactions
3
Author
DanielBeck93DanielBeck93
Participants
DanielBeck93DanielBeck93Roy214Roy214
Assignees
Roy214Roy214
Timeline (top)
commented ×2assigned ×1mentioned ×1subscribed ×1

Error Message

Value error, Model architectures ['JinaEmbeddingsV5Model'] are not supported for now. and also this error:

PR fix notes

PR #39575: Add Jina Embeddings v5 model support (fixes #38633)

Description (problem / solution / changelog)

Purpose

Add jina-embeddings-v5-text-small support

FIX #38633

Test Plan

Test Result

vllm serve

vllm serve ~/models/jina-embeddings-v5-text-small   --trust-remote-code --runner pooling --dtype float16   --hf-overrides '{"jina_task": "classification"}'
(APIServer pid=45059) INFO 04-11 11:28:49 [utils.py:299] 
(APIServer pid=45059) INFO 04-11 11:28:49 [utils.py:299]        █     █     █▄   ▄█
(APIServer pid=45059) INFO 04-11 11:28:49 [utils.py:299]  ▄▄ ▄█ █     █     █ ▀▄▀ █  version 0.19.1rc1.dev188+g8d0f908b9
(APIServer pid=45059) INFO 04-11 11:28:49 [utils.py:299]   █▄█▀ █     █     █     █  model   /root/models/jina-embeddings-v5-text-small
(APIServer pid=45059) INFO 04-11 11:28:49 [utils.py:299]    ▀▀  ▀▀▀▀▀ ▀▀▀▀▀ ▀     ▀
(APIServer pid=45059) INFO 04-11 11:28:49 [utils.py:299] 
(APIServer pid=45059) INFO 04-11 11:28:49 [utils.py:233] non-default args: {'model_tag': '/root/models/jina-embeddings-v5-text-small', 'model': '/root/models/jina-embeddings-v5-text-small', 'runner': 'pooling', 'trust_remote_code': True, 'dtype': 'float16', 'hf_overrides': {'jina_task': 'classification'}}
(APIServer pid=45059) INFO 04-11 11:28:49 [model.py:554] Resolved architecture: JinaEmbeddingsV5Model
(APIServer pid=45059) INFO 04-11 11:28:49 [config.py:835] Found sentence-transformers modules configuration.
....
(EngineCore pid=44017) INFO 04-11 11:24:17 [jina_embeddings_v5.py:126] Found adapter for task 'retrieval' at: /root/models/jina-embeddings-v5-text-small/adapters/retrieval
(EngineCore pid=44017) INFO 04-11 11:24:17 [jina_embeddings_v5.py:136] Loaded 392 adapter tensors (r=32, alpha=32, scaling=1.0000)
(EngineCore pid=44017) INFO 04-11 11:24:17 [jina_embeddings_v5.py:142] Built 196 LoRA pairs for merging
(EngineCore pid=44017) INFO 04-11 11:24:17 [weight_utils.py:904] Filesystem type for checkpoints: XFS. Checkpoint size: 1.11 GiB. Available RAM: 175.30 GiB.
...
(APIServer pid=8921) INFO 04-11 14:09:32 [launcher.py:46] Route: /v2/rerank, Methods: POST
(APIServer pid=8921) INFO:     Started server process [8921]
(APIServer pid=8921) INFO:     Waiting for application startup.
(APIServer pid=8921) INFO:     Application startup complete.

Inference with the model

curl -s http://localhost:8000/v1/embeddings   -H "Content-Type: application/json"   -d '{
    "model": "/root/models/jina-embeddings-v5-text-small",
    "input": ["Query: What is climate change?"]
  }' | python3 -m json.tool
{
    "id": "embd-bb716c01b9c32ba4",
    "object": "list",
    "created": 1775916661,
    "model": "/root/models/jina-embeddings-v5-text-small",
    "data": [
        {
            "index": 0,
            "object": "embedding",
            "embedding": [
                0.011783653870224953,
                -0.03300933912396431,
                -0.05155348777770996,
                -0.03261277452111244,
                0.09653531759977341,
                -0.042866818606853485,
                -0.014181929640471935,
...
<details> <summary> Essential Elements of an Effective PR Description Checklist </summary>
  • The purpose of the PR, such as "Fix some issue (link existing issues this PR will resolve)".
  • The test plan, such as providing test command.
  • The test results, such as pasting the results comparison before and after, or e2e results
  • (Optional) The necessary documentation update, such as updating supported_models.md and examples for a new model.
  • (Optional) Release notes update. If your change is user facing, please update the release notes draft in the Google Doc.
</details>

Changed files

  • docs/models/pooling_models/embed.md (modified, +7/-0)
  • tests/conftest.py (modified, +6/-0)
  • tests/models/language/pooling_mteb_test/mteb_embed_utils.py (modified, +26/-4)
  • tests/models/language/pooling_mteb_test/test_jina.py (modified, +25/-5)
  • tests/models/registry.py (modified, +4/-0)
  • vllm/model_executor/models/jina.py (modified, +149/-1)
  • vllm/model_executor/models/registry.py (modified, +1/-0)
RAW_BUFFERClick to expand / collapse

The model to consider.

The model I want to deploy is https://huggingface.co/jinaai/jina-embeddings-v5-text-small but I am getting

Value error, Model architectures ['JinaEmbeddingsV5Model'] are not supported for now.

and also this error:

ImportError: This modeling file requires the following packages that were not found in your environment: peft. Run pip install peft

The closest model vllm already supports.

https://huggingface.co/jinaai/jina-embeddings-v4

What's your difficulty of supporting the model you want?

No response

Before submitting a new issue...

  • Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.

extent analysis

TL;DR

The most likely fix is to install the missing peft package and consider using a supported model version, such as jina-embeddings-v4, until jina-embeddings-v5-text-small is supported.

Guidance

  • Install the peft package using pip install peft to resolve the ImportError.
  • Consider using the closest supported model, jina-embeddings-v4, as a temporary workaround.
  • Verify the list of supported models and their requirements to ensure compatibility with your environment.
  • Check the documentation and issue tracker for updates on when jina-embeddings-v5-text-small will be supported.

Notes

The jina-embeddings-v5-text-small model is not currently supported, and installing peft may not be sufficient to resolve the issue. The user may need to wait for an update or use a different model.

Recommendation

Apply workaround: Use jina-embeddings-v4 until jina-embeddings-v5-text-small is supported, as it is the closest supported model version.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…
#API rate limit#retriever error#indexing error#inference speed#output truncation

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING