Xenova HF Staff whitphx HF Staff commited on
Commit
6a8096d
·
verified ·
1 Parent(s): 348cce3

Add/update the quantized ONNX model files and README.md for Transformers.js v3 (#13)

Browse files

- Add/update the quantized ONNX model files and README.md for Transformers.js v3 (dcffea2098dd55f0d75605810d1c72860487eb46)


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

README.md CHANGED
@@ -15,7 +15,7 @@ npm install @huggingface/transformers
15
 
16
  **Example:** Generate music with `Xenova/musicgen-small`.
17
  ```js
18
- import { AutoTokenizer, MusicgenForConditionalGeneration } from '@huggingface/transformers';
19
 
20
  // Load tokenizer and model
21
  const tokenizer = await AutoTokenizer.from_pretrained('Xenova/musicgen-small');
@@ -53,4 +53,4 @@ We also released an online demo, which you can try yourself: https://huggingface
53
 
54
  ---
55
 
56
- 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`).
 
15
 
16
  **Example:** Generate music with `Xenova/musicgen-small`.
17
  ```js
18
+ import { AutoTokenizer, MusicgenForConditionalGeneration, RawAudio } from '@huggingface/transformers';
19
 
20
  // Load tokenizer and model
21
  const tokenizer = await AutoTokenizer.from_pretrained('Xenova/musicgen-small');
 
53
 
54
  ---
55
 
56
+ 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/build_delay_pattern_mask_q4f16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5073a48681f24d90c7ae6e5b6cb9e773acf55fbf89e690862336f88c94fbc2f6
3
+ size 25810
onnx/decoder_model_q4f16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63f43d8e7643f77d06e8775c11872bccdb82711a64e2e016f8722f427048911a
3
+ size 254059744
onnx/decoder_with_past_model_q4f16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c2d2867e79acce06cf482b9ee016436373ab5099f572e424a43e745d187db1d
3
+ size 225054044
onnx/encodec_decode_q4f16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03f1a78e6ff011133db35baf2b3f148c5b533e3829581b6c97cc464ace7294dc
3
+ size 59055828
onnx/text_encoder_q4f16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa929b9741c003c2b5b38deb44cbf2d774b5c011eb908df460c694f06851723b
3
+ size 97345526