Xenova HF Staff whitphx HF Staff commited on
Commit
cf71bcf
·
verified ·
1 Parent(s): c1fa1b6

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 (b4711f94961fd5f8cbb67c85138333c39d7faaf3)


Co-authored-by: Yuichiro Tachibana <[email protected]>

README.md CHANGED
@@ -5,4 +5,21 @@ library_name: transformers.js
5
 
6
  https://huggingface.co/OFA-Sys/chinese-clip-vit-large-patch14-336px 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 [🤗 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/OFA-Sys/chinese-clip-vit-large-patch14-336px 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:** Zero shot image classification.
16
+
17
+ ```js
18
+ import { pipeline } from '@huggingface/transformers';
19
+
20
+ const classifier = await pipeline('zero-shot-image-classification', 'Xenova/chinese-clip-vit-large-patch14-336px');
21
+ const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/tiger.jpg';
22
+ const output = await classifier(url, ['tiger', 'horse', 'dog']);
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:f304fad4c257063b482f823db9a6bf7fa08b23571b61b9ae678432148c849c41
3
+ size 292272495
onnx/model_q4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ccff68cd80ae802f50747f8e7a779bb3fb048e36d0b53090fe0c50e9dd2e5d5
3
+ size 316539577
onnx/model_q4f16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87c737a1a74a0ab7d7f6bf871c4bbc81dd83ffeba09ce205ef1d2cd33bb08320
3
+ size 255751285
onnx/model_uint8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0f4a4826ed9fdf381c6bc70bd063d6c2272e404162587bf05371cb0d1d0b0b1
3
+ size 410743502