Add/update the quantized ONNX model files and README.md for Transformers.js v3 (#2)
Browse files- Add/update the quantized ONNX model files and README.md for Transformers.js v3 (897bb176b9a3fdf5eb8a6de8924c2d5035478128)
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-Flan-T5-77M 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-Flan-T5-77M 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-Flan-T5-77M');
|
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 sha256:2a75ce74cbdeb4780e5d6ad3f80ddadae61c4924d0e8681835dcc852a66090d2
|
3 |
+
size 89503475
|
onnx/decoder_model_fp16.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15226d9bfea9bbcccf95a74b4d661be27cf20b2373d87fa042189728bd6c8f87
|
3 |
+
size 116389149
|
onnx/decoder_model_int8.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38dcb9dc27fe4d532ed9c800ed98a96edd972d6a6107f188058bef6ceaf3a1c8
|
3 |
+
size 58454816
|
onnx/decoder_model_q4.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a558b0732a1372c9317aafcc983d7fb0635911d8cc75b05872e9c3ef6611010f
|
3 |
+
size 92103875
|
onnx/decoder_model_q4f16.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0b88644f5c2afb6ecaf0c0fa84fb2e291bbd879d11118a7a2c106b4e0620f46
|
3 |
+
size 56580248
|
onnx/decoder_model_uint8.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:900edd718d63d44dcd34b4aee0b737cbe0a34d1957814a3f7236cb98fc68f80e
|
3 |
+
size 58454869
|
onnx/decoder_with_past_model_bnb4.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d1fa2fa603883af09e4ecd0ba7300846bb2027e06fb60d6ba74043299105816
|
3 |
+
size 87689295
|
onnx/decoder_with_past_model_fp16.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4820ac097d5a191c43ce2c1e198eee32899d9b5fd02df60e84c54fd23dd74e9a
|
3 |
+
size 110062088
|
onnx/decoder_with_past_model_int8.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8765d960cdfbccf35b45a993e738bbb77e2602040d71d3f87b93fcf47a471560
|
3 |
+
size 55251237
|
onnx/decoder_with_past_model_q4.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f545762f8f24ef11b52aa0ca60c3422ce21a532205a0233cf1a43fe17a3f495a
|
3 |
+
size 90093183
|
onnx/decoder_with_past_model_q4f16.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:030a9e076d1f5a264b576800036c433fd3f20b59db496dd521b13225cc7c508d
|
3 |
+
size 54772819
|
onnx/decoder_with_past_model_uint8.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:123a740a4309b4fa0c4e7bcf0ac2f1bae8f2c3c28f29457248c995a31464dc9f
|
3 |
+
size 55251283
|
onnx/encoder_model_bnb4.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8103152cf4d1cb878dd17e63588245feb00569ec3f6a69ec195ac8b7d68f4c41
|
3 |
+
size 76585753
|
onnx/encoder_model_int8.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6577ca55fd139e2baaf53737d990d771c6f28ccaec3d616744839e8fc3282a05
|
3 |
+
size 35548105
|
onnx/encoder_model_q4.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e638229b1c19e490e72aeeedd024ae8dce8707a202dd0e12e65b4c6947640377
|
3 |
+
size 77765041
|
onnx/encoder_model_q4f16.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28d22f2dfde5897a36bc1982e2958e61fba286ca454fde704767e3aa5bd0efa8
|
3 |
+
size 43669218
|
onnx/encoder_model_uint8.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45a92814c10b0d113130e511980a188ab4fe29fe8e30687e14e66d6eac2e879a
|
3 |
+
size 35548138
|