Add/update the quantized ONNX model files and README.md for Transformers.js v3
Browse files## Applied Quantizations
### β Based on `model.onnx` *with* slimming
```
None
```
β³ β `int8`: `model_int8.onnx` (added but JS-based E2E test failed)
```
/home/ubuntu/src/tjsmigration/node_modules/.pnpm/[email protected]/node_modules/onnxruntime-node/dist/backend.js:25
__classPrivateFieldGet(this, _OnnxruntimeSessionHandler_inferenceSession, "f").loadModel(pathOrBuffer, options);
^
Error: Could not find an implementation for ConvInteger(10) node with name '/first_convolution/Conv_quant'
at new OnnxruntimeSessionHandler (/home/ubuntu/src/tjsmigration/node_modules/.pnpm/[email protected]/node_modules/onnxruntime-node/dist/backend.js:25:92)
at Immediate.<anonymous> (/home/ubuntu/src/tjsmigration/node_modules/.pnpm/[email protected]/node_modules/onnxruntime-node/dist/backend.js:67:29)
at process.processImmediate (node:internal/timers:485:21)
Node.js v22.16.0
```
β³ β
`uint8`: `model_uint8.onnx` (added)
β³ β
`q4`: `model_q4.onnx` (added)
β³ β
`q4f16`: `model_q4f16.onnx` (added)
β³ β
`bnb4`: `model_bnb4.onnx` (added)
### β Based on `model.onnx` *with* slimming
```
None
```
β³ β `int8`: `model_int8.onnx` (added but JS-based E2E test failed)
```
/home/ubuntu/src/tjsmigration/node_modules/.pnpm/[email protected]/node_modules/onnxruntime-node/dist/backend.js:25
__classPrivateFieldGet(this, _OnnxruntimeSessionHandler_inferenceSession, "f").loadModel(pathOrBuffer, options);
^
Error: Could not find an implementation for ConvInteger(10) node with name '/first_convolution/Conv_quant'
at new OnnxruntimeSessionHandler (/home/ubuntu/src/tjsmigration/node_modules/.pnpm/[email protected]/node_modules/onnxruntime-node/dist/backend.js:25:92)
at Immediate.<anonymous> (/home/ubuntu/src/tjsmigration/node_modules/.pnpm/[email protected]/node_modules/onnxruntime-node/dist/backend.js:67:29)
at process.processImmediate (node:internal/timers:485:21)
Node.js v22.16.0
```
β³ β
`uint8`: `model_uint8.onnx` (added)
β³ β
`q4`: `model_q4.onnx` (added)
β³ β
`q4f16`: `model_q4f16.onnx` (added)
β³ β
`bnb4`: `model_bnb4.onnx` (added)
- README.md +17 -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
@@ -5,4 +5,21 @@ library_name: transformers.js
|
|
5 |
|
6 |
https://huggingface.co/hf-tiny-model-private/tiny-random-Swin2SRModel with ONNX weights to be compatible with Transformers.js.
|
7 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
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 [π€ Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).
|
|
|
5 |
|
6 |
https://huggingface.co/hf-tiny-model-private/tiny-random-Swin2SRModel with ONNX weights to be compatible with Transformers.js.
|
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:** Perform image feature extraction.
|
16 |
+
|
17 |
+
```js
|
18 |
+
import { pipeline } from '@huggingface/transformers';
|
19 |
+
|
20 |
+
const image_feature_extractor = await pipeline('image-feature-extraction', 'Xenova/tiny-random-Swin2SRModel');
|
21 |
+
const url = 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/cats.png';
|
22 |
+
const features = await image_feature_extractor(url);
|
23 |
+
```
|
24 |
+
|
25 |
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 [π€ Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55b37f22ab259382b7190887df0a1bc871a5b02de3579e3a26e93299aa4d77d5
|
3 |
+
size 274446
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9a6a46444f6d7012c3ac85927abd9045a1c9c82f5b249485cb0d85bfbd9563b
|
3 |
+
size 278614
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b560e06726dae352e12a631ea612a04308d44e9085613a31435c6dd345f34ba2
|
3 |
+
size 256148
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c13d47bfe38920c600c1f4199ccaea13158bac768da0d740d446e9b9a5c6c968
|
3 |
+
size 288118
|