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

## Applied Quantizations

### ✅ Based on `decoder_model.onnx` *with* slimming

↳ ✅ `fp16`: `decoder_model_fp16.onnx` (added)
↳ ✅ `int8`: `decoder_model_int8.onnx` (added)
↳ ✅ `uint8`: `decoder_model_uint8.onnx` (added)
↳ ✅ `q4`: `decoder_model_q4.onnx` (added)
↳ ✅ `q4f16`: `decoder_model_q4f16.onnx` (added)
↳ ✅ `bnb4`: `decoder_model_bnb4.onnx` (added)

### ✅ Based on `decoder_model.onnx` *with* slimming

↳ ✅ `fp16`: `decoder_model_fp16.onnx` (added)
↳ ✅ `int8`: `decoder_model_int8.onnx` (added)
↳ ✅ `uint8`: `decoder_model_uint8.onnx` (added)
↳ ✅ `q4`: `decoder_model_q4.onnx` (added)
↳ ✅ `q4f16`: `decoder_model_q4f16.onnx` (added)
↳ ✅ `bnb4`: `decoder_model_bnb4.onnx` (added)

### ❌ Based on `encoder_model.onnx` *with* slimming

```
None
```
↳ ❌ `int8`: `encoder_model_int8.onnx` (added but JS-based E2E test failed)
```
dtype not specified for "decoder_model_merged". Using the default dtype (fp32) for this device (cpu).
/home/ubuntu/src/tjsmigration/node_modules/.pnpm/[email protected]/node_modules/onnxruntime-node/dist/backend.js:25
__classPrivateFieldGet(this, _OnnxruntimeSessionHandler_inferenceSession, "f").loadModel(pathOrBuffer, options);
^

Error: Could not find an implementation for ConvInteger(10) node with name '/embeddings/patch_embeddings/projection/Conv_quant'
at new OnnxruntimeSessionHandler (/home/ubuntu/src/tjsmigration/node_modules/.pnpm/[email protected]/node_modules/onnxruntime-node/dist/backend.js:25:92)
at Immediate.<anonymous> (/home/ubuntu/src/tjsmigration/node_modules/.pnpm/[email protected]/node_modules/onnxruntime-node/dist/backend.js:67:29)
at process.processImmediate (node:internal/timers:485:21)

Node.js v22.16.0
```
↳ ✅ `uint8`: `encoder_model_uint8.onnx` (added)
↳ ✅ `q4`: `encoder_model_q4.onnx` (added)
↳ ✅ `q4f16`: `encoder_model_q4f16.onnx` (added)
↳ ✅ `bnb4`: `encoder_model_bnb4.onnx` (added)

### ❌ Based on `encoder_model.onnx` *with* slimming

```
None
```
↳ ❌ `int8`: `encoder_model_int8.onnx` (added but JS-based E2E test failed)
```
dtype not specified for "decoder_model_merged". Using the default dtype (fp32) for this device (cpu).
/home/ubuntu/src/tjsmigration/node_modules/.pnpm/[email protected]/node_modules/onnxruntime-node/dist/backend.js:25
__classPrivateFieldGet(this, _OnnxruntimeSessionHandler_inferenceSession, "f").loadModel(pathOrBuffer, options);
^

Error: Could not find an implementation for ConvInteger(10) node with name '/embeddings/patch_embeddings/projection/Conv_quant'
at new OnnxruntimeSessionHandler (/home/ubuntu/src/tjsmigration/node_modules/.pnpm/[email protected]/node_modules/onnxruntime-node/dist/backend.js:25:92)
at Immediate.<anonymous> (/home/ubuntu/src/tjsmigration/node_modules/.pnpm/[email protected]/node_modules/onnxruntime-node/dist/backend.js:67:29)
at process.processImmediate (node:internal/timers:485:21)

Node.js v22.16.0
```
↳ ✅ `uint8`: `encoder_model_uint8.onnx` (added)
↳ ✅ `q4`: `encoder_model_q4.onnx` (added)
↳ ✅ `q4f16`: `encoder_model_q4f16.onnx` (added)
↳ ✅ `bnb4`: `encoder_model_bnb4.onnx` (added)

### ✅ Based on `decoder_with_past_model.onnx` *with* slimming

↳ ✅ `fp16`: `decoder_with_past_model_fp16.onnx` (added)
↳ ✅ `int8`: `decoder_with_past_model_int8.onnx` (added)
↳ ✅ `uint8`: `decoder_with_past_model_uint8.onnx` (added)
↳ ✅ `q4`: `decoder_with_past_model_q4.onnx` (added)
↳ ✅ `q4f16`: `decoder_with_past_model_q4f16.onnx` (added)
↳ ✅ `bnb4`: `decoder_with_past_model_bnb4.onnx` (added)

### ✅ Based on `decoder_with_past_model.onnx` *with* slimming

↳ ✅ `fp16`: `decoder_with_past_model_fp16.onnx` (added)
↳ ✅ `int8`: `decoder_with_past_model_int8.onnx` (added)
↳ ✅ `uint8`: `decoder_with_past_model_uint8.onnx` (added)
↳ ✅ `q4`: `decoder_with_past_model_q4.onnx` (added)
↳ ✅ `q4f16`: `decoder_with_past_model_q4f16.onnx` (added)
↳ ✅ `bnb4`: `decoder_with_past_model_bnb4.onnx` (added)

### ❌ Based on `decoder_model_merged.onnx` *with* slimming

```
0%| | 0/1 [00:00<?, ?it/s]
Processing /tmp/tmpv07qia3n/decoder_model_merged.onnx: 0%| | 0/1 [00:00<?, ?it/s]

0%| | 0/6 [00:00<?, ?it/s][A

- Quantizing to fp16: 0%| | 0/6 [00:00<?, ?it/s][A/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 1.118331205418599e-09 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -4.765334793432885e-09 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 8.830656206271215e-09 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -2.0533679645495795e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -9.812860746194474e-09 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -3.51695454980927e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 8.398719053559489e-09 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -4.744606840745291e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -5.874542807760008e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 7.991577177790532e-09 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -5.6169927376004125e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 4.32548752371531e-09 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -4.2703192093540565e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 3.385328994909287e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -2.711802338239977e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 7.634087140218071e-09 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -4.2646148834535325e-09 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 5.9225204296353695e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -6.92422830184114e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 3.8164746030133756e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -5.606542430314221e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 2.952910094222716e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -2.9804627654783644e-09 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 3.322649888559681e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -2.7261572999037753e-09 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 1.9852429034017405e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -3.5895302286093056e-09 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 8.320770739089767e-09 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -3.843047657881016e-09 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 1.3270729404268877e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -2.861700920675503e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 6.242043770754435e-09 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -8.150554009489497e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float1

Files changed (23) hide show

README.md +3 -3
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_q4.onnx +3 -0
onnx/encoder_model_q4f16.onnx +3 -0
onnx/encoder_model_uint8.onnx +3 -0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ed918f9a438372dd40539f7c08b38ed2ee6566ef4c7c3c97d972d92bed497a7
-size 550244893

@@ -12,15 +12,15 @@ https://huggingface.co/facebook/nougat-base with ONNX weights to be compatible w
 ## Usage (Transformers.js)
-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:
 ```bash
-npm i @xenova/transformers
 ```
 You can then use the model to convert images of scientific PDFs into markdown like this:
 ```js
-import { pipeline } from '@xenova/transformers';
 // Create an image-to-text pipeline
 const pipe = await pipeline('image-to-text', 'Xenova/nougat-base');

+version https://git-lfs.github.com/spec/v1
+oid sha256:178fef87c92a77b73947d5541a32dad8a879c9fda7ec04ae785a4fc9746073a4
+size 345996608

+version https://git-lfs.github.com/spec/v1
+oid sha256:9dd9e2621e44f0850aacdd9202d8b46fb6d8e0eba6378b370a11f26a9c088779
+size 549565080

+version https://git-lfs.github.com/spec/v1
+oid sha256:0ef38c3ce1dddb94053a6a163dc7e2720f1c8dc761cd92cbe1852fdee2a28936
+size 275717861

+version https://git-lfs.github.com/spec/v1
+oid sha256:0f2df255fd246f1b05e31a8b49423feb08d28683908598348047a01037dc8850
+size 346411238

 version https://git-lfs.github.com/spec/v1
+oid sha256:faf02a49a718471e3de14342884543e6913812a9ef07c6c7f8961f70bacc7de1
+size 550253124

+version https://git-lfs.github.com/spec/v1
+oid sha256:76a4cc7763603dc8d637933ff82c1bbc6ef70236781d49b04965509b291fc817
+size 276490431

+version https://git-lfs.github.com/spec/v1
+oid sha256:f126e6a7b643c5aeb1a39a3b0ddbb39afb7881ed2da71b6bba79729cdf00fe71
+size 360095451

+version https://git-lfs.github.com/spec/v1
+oid sha256:1667a2bc291744929b7ade6bb439be6dd224d47129a2d87fe6cd3fd1f146b0c6
+size 235492901

+version https://git-lfs.github.com/spec/v1
+oid sha256:a635f1583fff4b344c718bd268a22f3d80d1d8074a42a55bd15af74a27384de7
+size 276490473

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:33b8ee8060c4118f1f5db0b51fb27aaa6136f78cf49530bb18e43dcd7e2fe93c
+size 359681550

+version https://git-lfs.github.com/spec/v1
+oid sha256:3f017354264713df63a1331807189ddbeea9850f8a72fbb347f02f2404807040
+size 234807622

+version https://git-lfs.github.com/spec/v1
+oid sha256:639d13ade62c506b7da92e99443655474aabeda0dcafec787560c053ca1cf0a3
+size 275717903

+version https://git-lfs.github.com/spec/v1
+oid sha256:898b2b92864d5428166ac7e1f8fc2d3c30384886013f54f590be8fd8486bc0cd
+size 334001000

+version https://git-lfs.github.com/spec/v1
+oid sha256:d815928857ec5c88fb5d7255154a80860b7f350950d8cd710bb00aab04e6a775
+size 507474982

+version https://git-lfs.github.com/spec/v1
+oid sha256:f5a7d1b6993fdcc19cd80250dc187ac20be6b4aebf6b93873f5d3c9e04411ca2
+size 254530303

+version https://git-lfs.github.com/spec/v1
+oid sha256:4e1327b63b645ea01cbfd759a8a7fa8e7cc67e9cf1a284a4a3a51d73874e260b
+size 346375382

+version https://git-lfs.github.com/spec/v1
+oid sha256:51bbb8840d0b45eaacb32b8771b4639b6e213d2509ec3c45810c5f3a376c6441
+size 222861124

+version https://git-lfs.github.com/spec/v1
+oid sha256:8fe1682e72ff43fb74a80b5ad6f38524b7c671528244f0158107b0b6080e7503
+size 254530337

+version https://git-lfs.github.com/spec/v1
+oid sha256:59b055721a6b60f870346af3a016a256522acd77d470d78653f68728050bdcf2
+size 46602584

+version https://git-lfs.github.com/spec/v1
+oid sha256:67ea64d1b8908ff4376fecb321a3fd7fc600bafe588a374817bd4bf093720584
+size 51221897

+version https://git-lfs.github.com/spec/v1
+oid sha256:0d3eddc9023f0933df857c7bc41e3840d1d63e95b026e1c1667644e8dee7d5d4
+size 44816260

+version https://git-lfs.github.com/spec/v1
+oid sha256:c0950da4a6e651bfa58616e0b27fb3842283ceace6e7cb9d6354eefd768e31da
+size 79070810