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 (fe3518e9a55b7e506a3a231a7bf04db4cd6194a2)
Co-authored-by: Yuichiro Tachibana <whitphx@users.noreply.huggingface.co>
- README.md +16 -0
- onnx/model_bnb4.onnx +3 -0
- onnx/model_int8.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 +6,20 @@ pipeline_tag: feature-extraction
|
|
| 6 |
|
| 7 |
https://huggingface.co/allenai/scibert_scivocab_uncased 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/allenai/scibert_scivocab_uncased 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:** Run feature extraction.
|
| 17 |
+
|
| 18 |
+
```js
|
| 19 |
+
import { pipeline } from '@huggingface/transformers';
|
| 20 |
+
|
| 21 |
+
const extractor = await pipeline('feature-extraction', 'Xenova/scibert_scivocab_uncased');
|
| 22 |
+
const output = await extractor('This is a simple test.');
|
| 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 [🤗 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 sha256:49a5e742f7864a4042c5a24431b5846f41d247a67ed7e96eefab75e5c7566d7a
|
| 3 |
+
size 145638366
|
onnx/model_int8.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4022242ee384cee2bae27997b4d35dd8c7fdfa6f564f843fca31b3fda845abb6
|
| 3 |
+
size 110058626
|
onnx/model_q4.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7addaaedca1987a701f210165d02d45bac41a9e7d29277513582e3e7cbb6a4f
|
| 3 |
+
size 150946254
|
onnx/model_q4f16.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5eb5b41626724e433358c43a5a245f0012f441ecd87105f24b6605ecdae1e8c9
|
| 3 |
+
size 96851579
|
onnx/model_uint8.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:049fcfc7fc68c4e1f71b017b3622fc87b473bc6bf527b4b4b0f4185e24ec5277
|
| 3 |
+
size 110058662
|