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 (c194f22687952c0afd639fab607e802d08ad65d5)
Co-authored-by: Yuichiro Tachibana <[email protected]>
- README.md +4 -5
- 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
@@ -7,15 +7,15 @@ https://huggingface.co/facebook/dinov2-large-imagenet1k-1-layer with ONNX weight
|
|
7 |
|
8 |
## Usage (Transformers.js)
|
9 |
|
10 |
-
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/@
|
11 |
```bash
|
12 |
-
npm i @
|
13 |
```
|
14 |
|
15 |
**Example:** Image classification w/ `Xenova/dinov2-base-imagenet1k-1-layer`.
|
16 |
|
17 |
```javascript
|
18 |
-
import { pipeline } from '@
|
19 |
|
20 |
// Create image classification pipeline
|
21 |
const classifier = await pipeline('image-classification', 'Xenova/dinov2-large-imagenet1k-1-layer');
|
@@ -23,11 +23,10 @@ const classifier = await pipeline('image-classification', 'Xenova/dinov2-large-i
|
|
23 |
// Classify an image
|
24 |
const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/cats.jpg';
|
25 |
const output = await classifier(url);
|
26 |
-
console.log(output)
|
27 |
// [{ label: 'tabby, tabby cat', score: 0.5089695453643799 }]
|
28 |
```
|
29 |
|
30 |
---
|
31 |
|
32 |
-
|
33 |
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`).
|
|
|
7 |
|
8 |
## Usage (Transformers.js)
|
9 |
|
10 |
+
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:
|
11 |
```bash
|
12 |
+
npm i @huggingface/transformers
|
13 |
```
|
14 |
|
15 |
**Example:** Image classification w/ `Xenova/dinov2-base-imagenet1k-1-layer`.
|
16 |
|
17 |
```javascript
|
18 |
+
import { pipeline } from '@huggingface/transformers';
|
19 |
|
20 |
// Create image classification pipeline
|
21 |
const classifier = await pipeline('image-classification', 'Xenova/dinov2-large-imagenet1k-1-layer');
|
|
|
23 |
// Classify an image
|
24 |
const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/cats.jpg';
|
25 |
const output = await classifier(url);
|
26 |
+
console.log(output);
|
27 |
// [{ label: 'tabby, tabby cat', score: 0.5089695453643799 }]
|
28 |
```
|
29 |
|
30 |
---
|
31 |
|
|
|
32 |
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:ccc7145fd1c5f725d8873fd342f85a0864749fe52cf950961684a5fccac2d0ec
|
3 |
+
size 183424523
|
onnx/model_q4.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d2a265fe3bf54e945c38d5786a65d98de4313bdf6c53de81fd6adff38a6e2f11
|
3 |
+
size 202297715
|
onnx/model_q4f16.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ba1540191be9c1a73abb9921ca2ef55f0e10a7b3e7da33eedcd0fe6a558dce4
|
3 |
+
size 176849445
|
onnx/model_uint8.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fed0b9f6a590a49b2cbdcf060d3a3fe3c9e54893331ab6e81c22ea8ea9670a31
|
3 |
+
size 307755482
|