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 (00b651c9de08ab93b84bf89fd7f204b9ed7607ba)
Co-authored-by: Yuichiro Tachibana <[email protected]>
- README.md +3 -6
- 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
@@ -8,18 +8,16 @@ tags:
|
|
8 |
|
9 |
https://huggingface.co/AmelieSchreiber/esm2_t6_8M_UR50D_sequence_classifier_v1 with ONNX weights to be compatible with Transformers.js.
|
10 |
|
11 |
-
|
12 |
-
|
13 |
## Usage (Transformers.js)
|
14 |
|
15 |
-
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/@
|
16 |
```bash
|
17 |
-
npm i @
|
18 |
```
|
19 |
|
20 |
**Example:** Protein sequence classification w/ `Xenova/esm2_t6_8M_UR50D_sequence_classifier_v1`.
|
21 |
```js
|
22 |
-
import { pipeline } from '@
|
23 |
|
24 |
// Create text classification pipeline
|
25 |
const classifier = await pipeline('text-classification', 'Xenova/esm2_t6_8M_UR50D_sequence_classifier_v1');
|
@@ -88,5 +86,4 @@ for (let i = 0; i < predictions.length; ++i) {
|
|
88 |
// Sequence: QPSASNCEKMSSYRPSLPSMSKGVPSSRSKSSPPYQ, Predicted class: 'Structural Proteins'
|
89 |
```
|
90 |
|
91 |
-
|
92 |
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`).
|
|
|
8 |
|
9 |
https://huggingface.co/AmelieSchreiber/esm2_t6_8M_UR50D_sequence_classifier_v1 with ONNX weights to be compatible with Transformers.js.
|
10 |
|
|
|
|
|
11 |
## Usage (Transformers.js)
|
12 |
|
13 |
+
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:
|
14 |
```bash
|
15 |
+
npm i @huggingface/transformers
|
16 |
```
|
17 |
|
18 |
**Example:** Protein sequence classification w/ `Xenova/esm2_t6_8M_UR50D_sequence_classifier_v1`.
|
19 |
```js
|
20 |
+
import { pipeline } from '@huggingface/transformers';
|
21 |
|
22 |
// Create text classification pipeline
|
23 |
const classifier = await pipeline('text-classification', 'Xenova/esm2_t6_8M_UR50D_sequence_classifier_v1');
|
|
|
86 |
// Sequence: QPSASNCEKMSSYRPSLPSMSKGVPSSRSKSSPPYQ, Predicted class: 'Structural Proteins'
|
87 |
```
|
88 |
|
|
|
89 |
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:c0f1db9d1d953b93d233a15434aec8144a164f49c028f9b40166ed7986b2e149
|
3 |
+
size 4941412
|
onnx/model_int8.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:baffbd276fa453d6f291de12e0adc62455e5164faa31a938d8dd17656cfb0655
|
3 |
+
size 7866436
|
onnx/model_q4.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1c6f5b4273c4d28db176334f9f51b8357d55d0c97958b434b197f44fafa9d42
|
3 |
+
size 5401924
|
onnx/model_q4f16.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b9b892db3608496b9316dfce528668df1c7102d2039e4a522bf62547b2b635b
|
3 |
+
size 4664322
|
onnx/model_uint8.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65d8aebe0e8c4f81576832fc27264437cce85f0b770456aed365680544ff6311
|
3 |
+
size 7866451
|