---
license: cc-by-nc-4.0
base_model: jinaai/jina-embeddings-v5-omni-nano
base_model_relation: quantized
library_name: transformers.js
pipeline_tag: feature-extraction
tags:
- feature-extraction
- sentence-similarity
- multimodal
- cross-modal-retrieval
- onnx
- webgpu
- transformers.js
- jina-embeddings
- embeddings
language:
- multilingual
---

# jina-embeddings-v5-omni-nano · ONNX

ONNX exports of [`jinaai/jina-embeddings-v5-omni-nano`](https://huggingface.co/jinaai/jina-embeddings-v5-omni-nano) for in-browser inference via [transformers.js](https://huggingface.co/docs/transformers.js) **v4** with WebGPU.

`jina-embeddings-v5-omni-nano` is a ~1.04 B-parameter multimodal embedding model that maps **text, images, audio, and video** into a single shared 768-dimensional L2-normalized space, enabling cross-modal retrieval without reindexing.

## Architecture

The base model is a LLaVA-style composition of three frozen encoders plus small trainable projectors, with per-task LoRA adapters. This repo's exports have the **`retrieval`** task adapter merged into the static weights.

| Tower | Backbone | Role |
|---|---|---|
| Text | EuroBERT-210m (loaded as a bidirectional Llama) | Text encoder |
| Vision | Qwen3-VL vision tower + spatial merger | Image and video frames |
| Audio | Whisper-large-v3 encoder + Qwen2.5-Omni audio adapter | Audio (16 kHz mono) |

Each tower is bundled with its retrieval projector AND a copy of the language model (which performs the final cross-modal fusion + last-token pooling), so the three ONNX graphs are independently loadable.

## Files

Three ONNX graphs, three quantization variants each. Every variant ships as a small `.onnx` schema + a large `.onnx.data` or `.onnx_data` external-weight sidecar (HF Hub-friendly layout, no 2 GB protobuf limits).

| Modality | fp32 | fp16 | q4f16 | Verified parity vs fp32 (fp16) |
|---|---:|---:|---:|---|
| Text   |  849 MB | 424 MB |  263 MB | cos = 1.000000 |
| Vision | 1247 MB | 622 MB |  460 MB | cos = 0.999998 |
| Audio  | 3400 MB | 1700 MB | 1465 MB | (fp16 doesn't load on CPU EP; verify on WebGPU) |

**For desktop WebGPU, use `q4f16`** — it's the smallest and runs natively on shader-int4 hardware. Use `fp16` if you need higher numerical fidelity or your GPU lacks int4 paths.

Every graph outputs a single tensor `sentence_embedding` of shape `[batch, 768]`, already L2-normalized — cosine similarity reduces to a dot product.

## Input constraints

**Text** (`text_model*.onnx`): inputs `input_ids` and `attention_mask`, both `[batch, seq]` with `seq` fully dynamic. Apply the asymmetric retrieval prefix convention before tokenizing: `Query: …` for queries, `Document: …` for corpus items.

**Vision** (`vision_model*.onnx`): the graph is traced at a fixed image-patch layout. `image_grid_thw` is folded as a constant (it drives `torch.linspace` inside Qwen3-VL's `fast_pos_embed_interpolate`, which dynamo cannot symbolicate). Resize every image to **224×224** before passing through `LlavaEuroBertProcessor` — that yields the exact shapes the graph expects:

```
input_ids        [batch, 271]    int64
attention_mask   [batch, 271]    int64
pixel_values     [1024, 1536]    float32
```

`image_grid_thw` is NOT an ONNX input (it's a constant). Don't pass it.

**Audio** (`audio_model*.onnx`): traced with a 5-second 16 kHz mono clip. The graph expects exactly:

```
input_ids                [batch, 125]      int64   (audio_token_id placeholders)
attention_mask           [batch, 125]      int64
input_features           [1, 128, 3000]    float32 (Whisper log-mel, 30s padded)
feature_attention_mask   [1, 3000]         int64   (frame-level, 500 ones for 5s of real audio)
```

Pad or truncate every clip to 5 s. Longer-clip chunking (sliding 5 s windows, average pooled embeddings) is a v2 follow-up.

## Use with transformers.js v4

### Text

```js
import { AutoTokenizer } from "@huggingface/transformers";
import * as ort from "onnxruntime-web";

const REPO = "shreyask/jina-embeddings-v5-omni-nano-ONNX";

const tok = await AutoTokenizer.from_pretrained(REPO);
const sess = await ort.InferenceSession.create(
  `https://huggingface.co/${REPO}/resolve/main/onnx/text_model_q4f16.onnx`,
  { executionProviders: ["webgpu", "wasm"] },
);

const { input_ids, attention_mask } = await tok(
  "Query: a saxophone solo",
  { return_tensors: "ort" },
);
const { sentence_embedding } = await sess.run({ input_ids, attention_mask });
// Float32Array of length 768, already L2-normalized.
```

### Vision

```js
import { AutoProcessor } from "@huggingface/transformers";
import * as ort from "onnxruntime-web";

const proc = await AutoProcessor.from_pretrained(REPO);
const sess = await ort.InferenceSession.create(
  `https://huggingface.co/${REPO}/resolve/main/onnx/vision_model_q4f16.onnx`,
  { executionProviders: ["webgpu", "wasm"] },
);

// Resize to 224x224 before passing in.
const inputs = await proc.apply_chat_template(
  [{ role: "user", content: [{ type: "image", image: imageBlob }] }],
  { add_generation_prompt: false, tokenize: true, return_dict: true, return_tensors: "ort" },
);
const { sentence_embedding } = await sess.run({
  input_ids: inputs.input_ids,
  attention_mask: inputs.attention_mask,
  pixel_values: inputs.pixel_values,
});
```

### Audio

Audio preprocessing isn't bundled in `LlavaEuroBertProcessor` — use Whisper's feature extractor directly and stamp `audio_token_id` placeholders into `input_ids`. See the [reference implementation](https://huggingface.co/jinaai/jina-embeddings-v5-omni-nano/blob/main/modeling_jina_embeddings_v5_omni.py) for the exact mel-spec → placeholder count plumbing.

## Cross-modal retrieval

All three towers project into the same 768-dim space, so a text query can rank images / audio / video corpus items (and vice versa) without re-indexing. Embeddings are L2-normalized, so cosine similarity is a dot product:

```js
const score = textVec.reduce((s, v, i) => s + v * imageVec[i], 0);
```

## How these were exported

- `torch` 2.11, `transformers` 5.8, `onnx` 1.21, `onnxruntime` 1.26
- **Text**: `torch.onnx.export(..., dynamo=True)`. The LlamaModel-based encoder exports cleanly through the dynamo path
- **Vision and audio**: `torch.onnx.export(..., dynamo=False)` (legacy TorchScript tracer). Dynamo refuses to specialize Qwen3-VL's data-dependent `torch.linspace`, and the GQA-aware SDPA is monkey-patched with a manual MatMul+Softmax for the trace's duration
- PEFT LoRA fused via `merge_and_unload(safe_merge=True)` so the `retrieval` task adapter is baked in
- fp16 cast via `onnxruntime.transformers.float16.convert_float_to_float16` (the `onnxconverter_common` path mishandles dynamo's `_to_copy` nodes)
- 4-bit quant via `onnxruntime.quantization.matmul_nbits_quantizer.MatMulNBitsQuantizer` (`bits=4, block_size=32, accuracy_level=4`)
- Two graph post-patches required for the audio tower's ORT-loadability: `Cast(to=int64)` inserted before every `Slice` index input (366 inserts), and `Unsqueeze(0)`/`Squeeze(0)` wrapped around the rank-2-input `AveragePool` (1 site)

## License

Inherited from the base model: **CC BY-NC 4.0**. Commercial use requires reaching out to `sales@jina.ai`.

## Citation

```bibtex
@misc{jina-embeddings-v5-omni-nano,
  author = {Jina AI},
  title  = {jina-embeddings-v5-omni-nano},
  year   = {2025},
  url    = {https://huggingface.co/jinaai/jina-embeddings-v5-omni-nano}
}
```