Add/update the quantized ONNX model files and README.md for Transformers.js v3 (#1)
Browse files- Add/update the quantized ONNX model files and README.md for Transformers.js v3 (bb4e82938f4a2ed58be42414bf3fcf390ee4a225)
Co-authored-by: Yuichiro Tachibana <[email protected]>
- README.md +18 -0
- onnx/model_bnb4.onnx +3 -0
- onnx/model_q4.onnx +3 -0
- onnx/model_q4f16.onnx +3 -0
- onnx/model_uint8.onnx +3 -0
README.md
CHANGED
|
@@ -6,4 +6,22 @@ pipeline_tag: zero-shot-object-detection
|
|
| 6 |
|
| 7 |
https://huggingface.co/google/owlvit-large-patch14 with ONNX weights to be compatible with Transformers.js.
|
| 8 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).
|
|
|
|
| 6 |
|
| 7 |
https://huggingface.co/google/owlvit-large-patch14 with ONNX weights to be compatible with Transformers.js.
|
| 8 |
|
| 9 |
+
## Usage (Transformers.js)
|
| 10 |
+
|
| 11 |
+
If you haven't already, you can install the [Transformers.js](https://huggingface.co/docs/transformers.js) JavaScript library from [NPM](https://www.npmjs.com/package/@huggingface/transformers) using:
|
| 12 |
+
```bash
|
| 13 |
+
npm i @huggingface/transformers
|
| 14 |
+
```
|
| 15 |
+
|
| 16 |
+
**Example:** Zero-shot object detection.
|
| 17 |
+
|
| 18 |
+
```js
|
| 19 |
+
import { pipeline } from '@huggingface/transformers';
|
| 20 |
+
|
| 21 |
+
const detector = await pipeline('zero-shot-object-detection', 'Xenova/owlvit-large-patch14');
|
| 22 |
+
const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/astronaut.png';
|
| 23 |
+
const candidate_labels = ['human face', 'rocket', 'helmet', 'american flag'];
|
| 24 |
+
const output = await detector(url, candidate_labels);
|
| 25 |
+
```
|
| 26 |
+
|
| 27 |
Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).
|
onnx/model_bnb4.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ce796edcb2008c3a54bc434de52328ad03d66e120a6e3ef381e1d97d3005977
|
| 3 |
+
size 391332775
|
onnx/model_q4.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99e5aa81459bab97dcb5f58579cc51c7d2cd4ec0c21c3841830f8e971d4f99d5
|
| 3 |
+
size 415731278
|
onnx/model_q4f16.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8876e84580170da9fc66ee7648d7ff80247e7b3e7681ac739f72756b4e00a1a
|
| 3 |
+
size 305907305
|
onnx/model_uint8.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a336a37c5c4502c679d3eff8aae143a32159f2bade69c731af5f8482c542baf8
|
| 3 |
+
size 446733499
|