---
library_name: transformers.js
base_model: tobil/qmd-query-expansion-1.7B
tags:
  - onnx
  - webgpu
  - transformers.js
  - qwen3
  - query-expansion
  - search
license: apache-2.0
---

# qmd-query-expansion-1.7B-ONNX

ONNX version of [tobil/qmd-query-expansion-1.7B](https://huggingface.co/tobil/qmd-query-expansion-1.7B) for use with [Transformers.js](https://huggingface.co/docs/transformers.js) v4 and WebGPU.

This is a fine-tuned Qwen3-1.7B model for query expansion in [QMD](https://github.com/tobi/qmd) (Query Markup Documents). Given a search query, it generates three types of expanded queries:

- **lex** — BM25-optimized keywords
- **vec** — Dense retrieval sentences for semantic search
- **hyde** — Hypothetical Document Embedding (a synthetic passage)

## Usage with Transformers.js

```javascript
import { pipeline } from "@huggingface/transformers";

const generator = await pipeline(
  "text-generation",
  "shreyask/qmd-query-expansion-1.7B-ONNX",
  { dtype: "q4", device: "webgpu" }
);

const output = await generator("/no_think Expand this search query: API versioning", {
  max_new_tokens: 256,
  do_sample: false,
});

console.log(output[0].generated_text);
// Expected output:
// lex: API versioning best practices REST version management
// vec: How to implement API versioning strategies in REST APIs
// hyde: This document discusses API versioning approaches including URL path versioning...
```

## Model Details

- **Base model**: [Qwen/Qwen3-1.7B](https://huggingface.co/Qwen/Qwen3-1.7B) (fine-tuned by [tobil](https://huggingface.co/tobil))
- **ONNX variant**: Q4 (4-bit MatMulNBits, block size 32)
- **Size**: ~2.2 GB
- **Exported with**: optimum + onnxruntime MatMulNBitsQuantizer
- **Intended use**: In-browser query expansion for search pipelines

## Conversion

Exported from the HuggingFace Transformers checkpoint using optimum-cli, then quantized to Q4:

```bash
optimum-cli export onnx -m tobil/qmd-query-expansion-1.7B --task text-generation output/
```

```python
from onnxruntime.quantization.matmul_nbits_quantizer import MatMulNBitsQuantizer
quant = MatMulNBitsQuantizer(
    model="output/model.onnx", bits=4, block_size=32,
    is_symmetric=True, accuracy_level=4,
)
quant.process()
quant.model.save_model_to_file("onnx/model_q4.onnx", use_external_data_format=True)
```

## Credits

- QMD by [Tobi Lutke](https://github.com/tobi/qmd)
- ONNX conversion by [shreyask](https://huggingface.co/shreyask)