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

#1
by whitphx - opened
README.md CHANGED
@@ -7,19 +7,19 @@ https://huggingface.co/WhereIsAI/UAE-Large-V1 with ONNX weights to be compatible
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/@xenova/transformers) using:
11
  ```bash
12
- npm i @xenova/transformers
13
  ```
14
 
15
  You can then use the model to compute embeddings like this:
16
 
17
  ```js
18
- import { pipeline } from '@xenova/transformers';
19
 
20
  // Create a feature-extraction pipeline
21
  const extractor = await pipeline('feature-extraction', 'Xenova/UAE-Large-V1', {
22
- quantized: true, // Set this to false to use the full (unquantized) model
23
  });
24
 
25
  // Compute sentence embeddings
@@ -36,7 +36,7 @@ console.log(output);
36
 
37
  Compute cosine similarity between the two sentences:
38
  ```js
39
- import { cos_sim } from '@xenova/transformers';
40
  console.log(cos_sim(output[0].data, output[1].data))
41
  // 0.9586893906734091
42
  ```
 
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
  You can then use the model to compute embeddings like this:
16
 
17
  ```js
18
+ import { pipeline } from '@huggingface/transformers';
19
 
20
  // Create a feature-extraction pipeline
21
  const extractor = await pipeline('feature-extraction', 'Xenova/UAE-Large-V1', {
22
+ dtype: "fp32" // Options: "fp32", "fp16", "q8", "q4"
23
  });
24
 
25
  // Compute sentence embeddings
 
36
 
37
  Compute cosine similarity between the two sentences:
38
  ```js
39
+ import { cos_sim } from '@huggingface/transformers';
40
  console.log(cos_sim(output[0].data, output[1].data))
41
  // 0.9586893906734091
42
  ```
onnx/model_bnb4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8180bdf448880cf623e5fbb806c53b37e0f58b694709ed086d171862e30fe817
3
+ size 298852122
onnx/model_int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:636207e6491b393f4acd3000b093aac57b7877b9ccba20d94db474addc5b2a13
3
+ size 335783482
onnx/model_q4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fa7c83e8b21e324f49df582e6ee7a4236856b392eb9ce5e3f429887428b760b
3
+ size 317725314
onnx/model_q4f16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa3be3b61f08f16839801110ba67e1c7defefd341d8cc17f1192abe8b2fe5aff
3
+ size 234646268
onnx/model_uint8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efc272790604c1cd4461d2791405de9f572a677b57d661f05175c0fdb7ef9e82
3
+ size 335783547