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 (943cdc5cc4e13e84f21b98243f7c609b671b9eee)
Co-authored-by: Yuichiro Tachibana <[email protected]>
- README.md +18 -0
- onnx/decoder_model_bnb4.onnx +3 -0
- onnx/decoder_model_fp16.onnx +3 -0
- onnx/decoder_model_int8.onnx +3 -0
- onnx/decoder_model_q4.onnx +3 -0
- onnx/decoder_model_q4f16.onnx +3 -0
- onnx/decoder_model_uint8.onnx +3 -0
- onnx/decoder_with_past_model_bnb4.onnx +3 -0
- onnx/decoder_with_past_model_fp16.onnx +3 -0
- onnx/decoder_with_past_model_int8.onnx +3 -0
- onnx/decoder_with_past_model_q4.onnx +3 -0
- onnx/decoder_with_past_model_q4f16.onnx +3 -0
- onnx/decoder_with_past_model_uint8.onnx +3 -0
- onnx/encoder_model_bnb4.onnx +3 -0
- onnx/encoder_model_int8.onnx +3 -0
- onnx/encoder_model_q4.onnx +3 -0
- onnx/encoder_model_q4f16.onnx +3 -0
- onnx/encoder_model_uint8.onnx +3 -0
README.md
CHANGED
@@ -5,4 +5,22 @@ library_name: transformers.js
|
|
5 |
|
6 |
https://huggingface.co/MBZUAI/LaMini-T5-223M 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/MBZUAI/LaMini-T5-223M 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:** Text-to-text generation.
|
16 |
+
|
17 |
+
```js
|
18 |
+
import { pipeline } from '@huggingface/transformers';
|
19 |
+
|
20 |
+
const generator = await pipeline('text2text-generation', 'Xenova/LaMini-T5-223M');
|
21 |
+
const output = await generator('how can I become more healthy?', {
|
22 |
+
max_new_tokens: 100,
|
23 |
+
});
|
24 |
+
```
|
25 |
+
|
26 |
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/decoder_model_bnb4.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:120609f52209c1f809b982f61406a41459bb7040179e9ccd16fe6f20778ad546
|
3 |
+
size 162831208
|
onnx/decoder_model_fp16.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3f59dc13edf18a22fa96300c70614112fddc3afc40a1ae6ef1e658f005f3a3d
|
3 |
+
size 276200771
|
onnx/decoder_model_int8.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:929d7761bea2a6d5b6eb7023f1337e32b4a63ae10a26115bf621b7d2794ebba3
|
3 |
+
size 237178354
|
onnx/decoder_model_q4.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8f85059889311a6828b7cbed69c0180fce468ab2bee17e21a1e5c3f45649db1
|
3 |
+
size 169908232
|
onnx/decoder_model_q4f16.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e801ded2fbaf75461f1b4dc6f8eca23ea6339f10ac3665fa5a3476798ee4f9d6
|
3 |
+
size 113427317
|
onnx/decoder_model_uint8.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:523d9f7b86c1f78f6b57e6f6aa3ddb2ddc5dd52b87cb22bc34b04825359ae664
|
3 |
+
size 237178416
|
onnx/decoder_with_past_model_bnb4.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebcab6876837f5396d8f3f7b1b845fe9081ad2ad8ecb45a0f134f60be0a4a4d4
|
3 |
+
size 154802567
|
onnx/decoder_with_past_model_fp16.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28de892aa3c3ad0fbf23808652753041c1756ae7de356c27ed68a246fd7444dd
|
3 |
+
size 247836916
|
onnx/decoder_with_past_model_int8.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:391b2f3ca11a0d7971142598c0f859da0795af6d58cc62eebef447e0cde29509
|
3 |
+
size 222936950
|
onnx/decoder_with_past_model_q4.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b32d5a830bf78eb5db716024bc816fa026cb23f9bbaa2c6aa2c1d22e1430986
|
3 |
+
size 160995023
|
onnx/decoder_with_past_model_q4f16.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ead6a766e4fb51989f95944ccf49c9e9fe211c9df4ef8385094399592305415f
|
3 |
+
size 105408791
|
onnx/decoder_with_past_model_uint8.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23ea7ec0e243d5ee1903680342a628fcb13b2e2c91f151f30b00460b18247b45
|
3 |
+
size 222936994
|
onnx/encoder_model_bnb4.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d357a61f1ee8c2ad59c08ba6cf50fc9cd83b83fd25344cedbfd77e57c33dffc
|
3 |
+
size 146712592
|
onnx/encoder_model_int8.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:91c99106e5b887aed19d31d7ce7bed11e0956dcf7f8d9ae51c1baef942ba3ac7
|
3 |
+
size 109918758
|
onnx/encoder_model_q4.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2afe8a387100cb39fbb2ec6a0a7f1fce4aa27d9bca57ef40c0d0f860abfa70b0
|
3 |
+
size 152020480
|
onnx/encoder_model_q4f16.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75935f4f109cb3ecbc74ecfda231362a10c73e588cf4a1ca3a91aeea8f9d071a
|
3 |
+
size 97325051
|
onnx/encoder_model_uint8.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d2b7a7d313e7ee4c1ad31b231399143b96c7a910de000f7e95dee4c7260ecf0
|
3 |
+
size 109918798
|