Hugging Face's logo

Xenova
/
opus-mt-vi-en

Translation
Transformers.js
ONNX
marian
text2text-generation
Model card Files
xet
 Community
1

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

#1
by whitphx - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+68
-2
whitphx

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

↳ ✅ 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

↳ ✅ 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 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/tmpb_rogd72/decoder_model_merged.onnx:   0%|          | 0/1 [00:00<?, ?it/s]

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

 - Quantizing to fp16:   0%|          | 0/6 [00:00<?, ?it/s]/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 1.515640057903056e-09 will be truncated to 1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -5.1556581226464e-10 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 1.9743053414345013e-08 will be truncated to 1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -2.4268423715056997e-08 will be truncated to -1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -6.235465832560294e-08 will be truncated to -1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 5.614439047008091e-08 will be truncated to 1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 6.23651388309554e-08 will be truncated to 1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -7.726288053788721e-09 will be truncated to -1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -2.943271937283498e-08 will be truncated to -1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 5.201072283966823e-08 will be truncated to 1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -3.392046821204531e-08 will be truncated to -1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 7.111785294000583e-08 will be truncated to 1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -2.992969427850767e-08 will be truncated to -1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -7.367273013869635e-08 will be truncated to -1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 6.336982494303811e-08 will be truncated to 1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -1.901945445581532e-08 will be truncated to -1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -9.716459459241378e-08 will be truncated to -1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -4.3412669015197025e-08 will be truncated to -1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 4.001282150056795e-08 will be truncated to 1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -3.92825789674589e-08 will be truncated to -1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 3.0937499229111154e-09 will be truncated to 1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -4.7417124449111725e-08 will be truncated to -1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -6.631412929891667e-08 will be truncated to -1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 3.466136533347708e-08 will be truncated to 1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -4.053306668083678e-08 will be truncated to -1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -7.994788830956168e-08 will be truncated to -1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -4.342485837582899e-08 will be truncated to -1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -5.2110692649876e-08 will be truncated to -1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -4.841696465973655e-08 will be truncated to -1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -5.560578220098478e-09 will be truncated to -1e-07
  warnings.warn(

 - Quantizing to fp16:   0%|          | 0/6 [00:03<?, ?it/s]

Processing /tmp/tmpb_rogd72/decoder_model_merged.onnx:   0%|          | 0/1 [00:03<?, ?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)

 Add/update the quantized ONNX model files and README.md for Transformers.js v300b90cc3
Xenova changed pull request status to merged

Sign up or log in to comment