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 (cfb6d22d081d923c8a58005d78741978edff29e8)
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-T5-738M 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-T5-738M 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-T5-738M');
|
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 sha256:5fdc9646ea4530a8a51ba46726d064608199818728918cb53aacbb8fb004b5e5
|
3 |
+
size 359009469
|
onnx/decoder_model_fp16.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85fed1331641fb40c5cb7375fbea3e2deddf0c268c335598a871924e4d6a2a91
|
3 |
+
size 871842343
|
onnx/decoder_model_int8.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5f3f550fdb2d989de335da72ce2cdebd93097f76bdaa8b4ee6074dadb98942a
|
3 |
+
size 568325153
|
onnx/decoder_model_q4.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e23d9d9c930cbb8db109097c7c3ae7461024c0c6c927a73e057df4ca2349c95e
|
3 |
+
size 384173349
|
onnx/decoder_model_q4f16.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55281bf4010c4800e39e6f2e242f0f0c5508ccba23e19e161c038aa0ec57fe75
|
3 |
+
size 293064050
|
onnx/decoder_model_uint8.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80fbb1596286cc2c76a786aee9ee0d38fe74492158ab8b3bd012a15aa14cdda9
|
3 |
+
size 568325291
|
onnx/decoder_with_past_model_bnb4.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:963680abf71dd83b0bf877135be08432bfd5c4e43a1013bd1e6a61a505bff7a4
|
3 |
+
size 330562780
|
onnx/decoder_with_past_model_fp16.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ccf5c6a07f59e03eff83b449eee04498e730e07bc0ff0d6ce0ff0dfc53f88a1b
|
3 |
+
size 771071401
|
onnx/decoder_with_past_model_int8.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2884387740bbcdfdf386dc7d76062777b8810617af5a1b97c0ab9b5173e723cd
|
3 |
+
size 517819197
|
onnx/decoder_with_past_model_q4.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01aa405f3b18fb99593c896eb32da69fa178826b44d3842d98190a23bd97759b
|
3 |
+
size 352581316
|
onnx/decoder_with_past_model_q4f16.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9df0f47e73c6d7cf04182a253a131d8bf9ebb20fdc05123a32942a3cfaa609a
|
3 |
+
size 264637747
|
onnx/decoder_with_past_model_uint8.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:706accfa0dadfe6799f67c0b024b63c91f241976f213d6f03896e7baeb96fa38
|
3 |
+
size 517819307
|
onnx/encoder_model_bnb4.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5955c8307978b3c4b2b31382156c38f57bd475ede243e6f836a90ce2c520aa1
|
3 |
+
size 301981521
|
onnx/encoder_model_int8.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:287ae3518dc5761aa0a8f94d014483aa14dddf73aeddcd46898c21fa3a82e16b
|
3 |
+
size 335545678
|
onnx/encoder_model_q4.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36240502b80e4110ba02bcc03837b2dfab5d8bc5d543ec95156eacb5d72d9e18
|
3 |
+
size 320854713
|
onnx/encoder_model_q4f16.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9130920d8f28405214a896cb5fc00c772b4032f279a5183607fabc49d602c69
|
3 |
+
size 236081587
|
onnx/encoder_model_uint8.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5fadb4215a9323434e1b0f6fb277abe4d7a244b8d0ba7f315271074f731270b7
|
3 |
+
size 335545738
|