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 (795f0fdc5f9c6ba93eb13d3d8590826736d6a909)
Co-authored-by: Yuichiro Tachibana <[email protected]>
- README.md +26 -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_merged_bnb4.onnx +3 -0
- onnx/decoder_model_merged_fp16.onnx +2 -2
- onnx/decoder_model_merged_int8.onnx +3 -0
- onnx/decoder_model_merged_q4.onnx +3 -0
- onnx/decoder_model_merged_q4f16.onnx +3 -0
- onnx/decoder_model_merged_uint8.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
|
@@ -6,4 +6,30 @@ pipeline_tag: summarization
|
|
| 6 |
|
| 7 |
https://huggingface.co/facebook/bart-large-xsum with ONNX weights to be compatible with Transformers.js.
|
| 8 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
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`).
|
|
|
|
| 6 |
|
| 7 |
https://huggingface.co/facebook/bart-large-xsum with ONNX weights to be compatible with Transformers.js.
|
| 8 |
|
| 9 |
+
## Usage (Transformers.js)
|
| 10 |
+
|
| 11 |
+
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:
|
| 12 |
+
```bash
|
| 13 |
+
npm i @huggingface/transformers
|
| 14 |
+
```
|
| 15 |
+
|
| 16 |
+
**Example:** Summarization.
|
| 17 |
+
|
| 18 |
+
```js
|
| 19 |
+
import { pipeline } from '@huggingface/transformers';
|
| 20 |
+
|
| 21 |
+
const generator = await pipeline('summarization', 'Xenova/bart-large-xsum');
|
| 22 |
+
const text = 'The tower is 324 metres (1,063 ft) tall, about the same height as an 81-storey building, ' +
|
| 23 |
+
'and the tallest structure in Paris. Its base is square, measuring 125 metres (410 ft) on each side. ' +
|
| 24 |
+
'During its construction, the Eiffel Tower surpassed the Washington Monument to become the tallest ' +
|
| 25 |
+
'man-made structure in the world, a title it held for 41 years until the Chrysler Building in New ' +
|
| 26 |
+
'York City was finished in 1930. It was the first structure to reach a height of 300 metres. Due to ' +
|
| 27 |
+
'the addition of a broadcasting aerial at the top of the tower in 1957, it is now taller than the ' +
|
| 28 |
+
'Chrysler Building by 5.2 metres (17 ft). Excluding transmitters, the Eiffel Tower is the second ' +
|
| 29 |
+
'tallest free-standing structure in France after the Millau Viaduct.';
|
| 30 |
+
const output = await generator(text, {
|
| 31 |
+
max_new_tokens: 100,
|
| 32 |
+
});
|
| 33 |
+
```
|
| 34 |
+
|
| 35 |
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 sha256:8793af5d29853c6d9aa82bb5627bff7cfe12d99ec1ccdf7b0b73a564d7540c83
|
| 3 |
+
size 324819020
|
onnx/decoder_model_fp16.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b917d0b9973cf7b370a54dc3696618405bb473cf927dc6150cd9c439390a065f
|
| 3 |
+
size 508696917
|
onnx/decoder_model_int8.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee0118a97f0c9fa018b053e545318e777989e9a9afaa1917d28f342edf64531e
|
| 3 |
+
size 255464148
|
onnx/decoder_model_merged_bnb4.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad35cf77ca8e165e9d87756f71a37b87e716019d95eb350481d145b61ae3f8da
|
| 3 |
+
size 325603874
|
onnx/decoder_model_merged_fp16.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3848e608fa805041c20017fc8df6bace402c0a69903a0d06a5d74b4084a77d8f
|
| 3 |
+
size 509382753
|
onnx/decoder_model_merged_int8.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46bf98966f20ceeb0d60cce6ab7bf39ed8293f2fc59df81fa4675d2b39d8f168
|
| 3 |
+
size 256355663
|
onnx/decoder_model_merged_q4.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7b70d5383c5e09ae99e3755e0be213ac3455ab4f68bf5f6b985bf7a3b08bef8
|
| 3 |
+
size 338184950
|
onnx/decoder_model_merged_q4f16.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:629188db2253a7cb90e7beec31fdd635d7bb50ffc60a399935e6bf35d28ffadb
|
| 3 |
+
size 220006815
|
onnx/decoder_model_merged_uint8.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88e71d9ee02e4f99a34b97fe819e499ed9c710f6a922e433c9afa3b39a7a28c4
|
| 3 |
+
size 256355726
|
onnx/decoder_model_q4.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ddccc4389387358f45268446973a4b257ba8308cad7485355c69eb9bfd7f846
|
| 3 |
+
size 337400960
|
onnx/decoder_model_q4f16.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a5cb3d977bd161a5a1fd79e14e9f0b9473aa6513210244ed4c00a7d85c618b69
|
| 3 |
+
size 219307779
|
onnx/decoder_model_uint8.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:efdd0da64d995efa5ce562be5619144863b910fba44017672052ada7452a01d2
|
| 3 |
+
size 255464211
|
onnx/decoder_with_past_model_bnb4.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f5888174ba2ea86662772638498b103b3e7fe227b561ca413159ca49bd6968c9
|
| 3 |
+
size 310431387
|
onnx/decoder_with_past_model_fp16.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f4ce7684619b62af68f575d9976e9db5187066296332261c82d4af168ab7a1f
|
| 3 |
+
size 458195908
|
onnx/decoder_with_past_model_int8.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0509adf6a23490273da94d94b8e69ff77bd8070c7905b5e8e033117d4a4411cc
|
| 3 |
+
size 230046616
|
onnx/decoder_with_past_model_q4.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e0b3face83a1f0635b8b5b8f52875854a381ce8212384110826fdfd7bc200bc
|
| 3 |
+
size 321440655
|
onnx/decoder_with_past_model_q4f16.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a110ee6120c91cf3c339a7b0e2e19e2a625c734f8f891999df26f0b467f391a8
|
| 3 |
+
size 204979090
|
onnx/decoder_with_past_model_uint8.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bedb99b06a2367ba6b32a7800396195f657cff856a72dc635735486728d4e3d5
|
| 3 |
+
size 230046667
|
onnx/encoder_model_bnb4.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d40e5630221e57e673ea22610f893a75b34021880731372d46c2d1aac6bd913c
|
| 3 |
+
size 295912467
|
onnx/encoder_model_int8.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d304f1422d1e4a418d028e6fbfea39c5cbef90cceec4e37a5ea704ea1897d04f
|
| 3 |
+
size 204472178
|
onnx/encoder_model_q4.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9fd017b3489a8025c10c8d9973f5cf18ec085ab7d2e6b9aa61f7e4b9927fa0b
|
| 3 |
+
size 305349063
|
onnx/encoder_model_q4f16.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8bf8d0d2be3ed2027a91840ffe05f73457948da88ee8177ff907549b1a81f52a
|
| 3 |
+
size 190546742
|
onnx/encoder_model_uint8.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ebe9d46358044e69908239d67ccaae2ebf759cdc1ea4c4f76d9e17406ed46fd
|
| 3 |
+
size 204472217
|