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

by whitphx - opened Jul 14, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+68

-2

Add/update the quantized ONNX model files and README.md for Transformers.js v381a747e9

whitphx

Jul 14, 2025

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

✅ Based on `encoder_model.onnx` with slimming

↳ ✅ int8: encoder_model_int8.onnx (added)
↳ ✅ 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

✅ 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

❌ Based on `decoder_model_merged.onnx` with slimming

0%|          | 0/1 [00:00<?, ?it/s]
Processing /tmp/tmpxbsob8ix/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 3.167758499955653e-09 will be truncated to 1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -2.2015654577156596e-10 will be truncated to -1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 2.5824347105185552e-08 will be truncated to 1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 1.6512606393348506e-08 will be truncated to 1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -3.782331603474631e-08 will be truncated to -1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:85: UserWarning: the float32 number -3.4028234663852886e+38 will be truncated to -10000.0
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 3.1959144219939617e-09 will be truncated to 1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 6.033525323800859e-08 will be truncated to 1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -2.9533312684293378e-08 will be truncated to -1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 4.0840788528839767e-08 will be truncated to 1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -6.851023215403984e-08 will be truncated to -1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -3.4313686114728625e-08 will be truncated to -1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 1.4718946950154077e-08 will be truncated to 1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 9.294224412315089e-08 will be truncated to 1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -7.819900105232591e-08 will be truncated to -1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -7.215111708092081e-08 will be truncated to -1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 3.580309027029216e-08 will be truncated to 1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -9.367174413910107e-08 will be truncated to -1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 2.47130422792452e-08 will be truncated to 1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -3.0298064501721456e-08 will be truncated to -1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 1.0144907136577785e-08 will be truncated to 1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -7.20404287335441e-08 will be truncated to -1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -2.5511303292091725e-08 will be truncated to -1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 2.0711153680963434e-08 will be truncated to 1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -4.2068233341296946e-09 will be truncated to -1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 9.636061548690122e-08 will be truncated to 1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -4.3503906033137696e-10 will be truncated to -1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -1.2583442732250205e-08 will be truncated to -1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -4.225162442139663e-08 will be truncated to -1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -8.442573573574919e-08 will be truncated to -1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 6.199302760023784e-08 will be truncated to 1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -6.319442036328837e-08 will be truncated to -1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -5.3112898967810906e-08 will be truncated to -1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 2.3611525179489945e-08 will be truncated to 1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -8.38243892076207e-08 will be truncated to -1e-07
  warnings.warn(

 - Quantizing to fp16:   0%|          | 0/6 [00:04<?, ?it/s]

Processing /tmp/tmpxbsob8ix/decoder_model_merged.onnx:   0%|          | 0/1 [00:04<?, ?it/s]
Traceback (most recent call last):
  File "<frozen runpy>", line 198, in _run_module_as_main
  File "<frozen runpy>", line 88, in _run_code
  File "/home/ubuntu/src/tjsmigration/transformers.js/scripts/quantize.py", line 377, in <module>
    main()
  File "/home/ubuntu/src/tjsmigration/transformers.js/scripts/quantize.py", line 374, in main
    quantize(input_folder, output_folder, quantization_args)
  File "/home/ubuntu/src/tjsmigration/transformers.js/scripts/quantize.py", line 309, in quantize
    quantize_fp16(
  File "/home/ubuntu/src/tjsmigration/transformers.js/scripts/quantize.py", line 223, in quantize_fp16
    check_and_save_model(model_fp16, save_path)
  File "/home/ubuntu/src/tjsmigration/transformers.js/scripts/utils.py", line 29, in check_and_save_model
    strict_check_model(model)
  File "/home/ubuntu/src/tjsmigration/transformers.js/scripts/utils.py", line 21, in strict_check_model
    raise e
  File "/home/ubuntu/src/tjsmigration/transformers.js/scripts/utils.py", line 16, in strict_check_model
    onnx.checker.check_model(model_or_path, full_check=True)
  File "/home/ubuntu/.cache/uv/archive-v0/7hYcxZ8pwavXeKpAYRaHY/lib/python3.12/site-packages/onnx/checker.py", line 179, in check_model
    C.check_model(
onnx.onnx_cpp2py_export.shape_inference.InferenceError: [ShapeInferenceError] Inference error(s): (op_type:If, node name: optimum::if): [ShapeInferenceError] Inference error(s): (op_type:Add, node name: /model/decoder/embed_positions/Add): [ShapeInferenceError] Inferred shape and existing shape differ in rank: (1) vs (0)

✅ Based on `decoder_model_merged.onnx` without slimming

↳ ✅ fp16: decoder_model_merged_fp16.onnx (replaced because it was invalid)
↳ ✅ int8: decoder_model_merged_int8.onnx (added)
↳ ✅ uint8: decoder_model_merged_uint8.onnx (added)
↳ ✅ q4: decoder_model_merged_q4.onnx (added)
↳ ✅ q4f16: decoder_model_merged_q4f16.onnx (added)
↳ ✅ bnb4: decoder_model_merged_bnb4.onnx (added)

Xenova changed pull request status to merged Jul 14, 2025

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment

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

Applied Quantizations

✅ Based on decoder_model.onnx with slimming

✅ Based on decoder_model.onnx with slimming

✅ Based on encoder_model.onnx with slimming

✅ Based on encoder_model.onnx with slimming

✅ Based on decoder_with_past_model.onnx with slimming

✅ Based on decoder_with_past_model.onnx with slimming

❌ Based on decoder_model_merged.onnx with slimming

✅ Based on decoder_model_merged.onnx without slimming

✅ Based on `decoder_model.onnx` with slimming

✅ Based on `decoder_model.onnx` with slimming

✅ Based on `encoder_model.onnx` with slimming

✅ Based on `encoder_model.onnx` with slimming

✅ Based on `decoder_with_past_model.onnx` with slimming

✅ Based on `decoder_with_past_model.onnx` with slimming

❌ Based on `decoder_model_merged.onnx` with slimming

✅ Based on `decoder_model_merged.onnx` without slimming