Hugging Face's logo

Xenova
/
opus-mt-fr-ru

Translation
Transformers.js
ONNX
marian
text2text-generation
Model card Files
xet
Community
1
whitphx HF Staff commited on
Commit
7291044
·
verified ·
1 Parent(s): ae2487c

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

Browse files

## 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/tmpcnqp8ph4/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 7.997064677134347e-10 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -6.797636897815096e-10 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -4.484200033516572e-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:92: UserWarning: the float32 number -3.0436289932822547e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 7.707421190161767e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 4.95706267145124e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -4.5924156921728354e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -8.378425775390497e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 7.040468830155078e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 2.1039372910536258e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -3.8115281597583817e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 9.064721240292783e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 4.212202853182134e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 7.046521943721018e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 3.407820869938405e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 6.667647767244489e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -5.739771680168815e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 4.266606978831078e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -4.917734841569654e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -6.085461734528508e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -2.1971937158582477e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 6.265831586915738e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 3.241369128659244e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -8.638192383614296e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -1.7165598720225717e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -3.5840244549945055e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 3.424865502310581e-09 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -1.7803628571400054e-09 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 1.3238699914097651e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -3.074934795677109e-08 will be truncated to -1e-07
warnings.warn(

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

Processing /tmp/tmpcnqp8ph4/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)

Files changed (23) hide show
  1. onnx/decoder_model_bnb4.onnx +3 -0
  2. onnx/decoder_model_fp16.onnx +3 -0
  3. onnx/decoder_model_int8.onnx +3 -0
  4. onnx/decoder_model_merged_bnb4.onnx +3 -0
  5. onnx/decoder_model_merged_fp16.onnx +2 -2
  6. onnx/decoder_model_merged_int8.onnx +3 -0
  7. onnx/decoder_model_merged_q4.onnx +3 -0
  8. onnx/decoder_model_merged_q4f16.onnx +3 -0
  9. onnx/decoder_model_merged_uint8.onnx +3 -0
  10. onnx/decoder_model_q4.onnx +3 -0
  11. onnx/decoder_model_q4f16.onnx +3 -0
  12. onnx/decoder_model_uint8.onnx +3 -0
  13. onnx/decoder_with_past_model_bnb4.onnx +3 -0
  14. onnx/decoder_with_past_model_fp16.onnx +3 -0
  15. onnx/decoder_with_past_model_int8.onnx +3 -0
  16. onnx/decoder_with_past_model_q4.onnx +3 -0
  17. onnx/decoder_with_past_model_q4f16.onnx +3 -0
  18. onnx/decoder_with_past_model_uint8.onnx +3 -0
  19. onnx/encoder_model_bnb4.onnx +3 -0
  20. onnx/encoder_model_int8.onnx +3 -0
  21. onnx/encoder_model_q4.onnx +3 -0
  22. onnx/encoder_model_q4f16.onnx +3 -0
  23. onnx/encoder_model_uint8.onnx +3 -0
onnx/decoder_model_bnb4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a614f8c088dbd7039cd65b8c8571912e9e64217e8f428c021851fe8104edb055
3
+ size 147810038
onnx/decoder_model_fp16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40580e9adf224f157d66b5217328661acb5fa65e92553a9ed6a0ce2b2d09d178
3
+ size 117286340
onnx/decoder_model_int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3df90a6165a415b324f83048af4f6f8b3273b3dc5e31bd1944a359307d496d2f
3
+ size 191058534
onnx/decoder_model_merged_bnb4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fe155f9d256367bee4755b08a02b924cbe70f2fe048daee35c785fed02293fc
3
+ size 148067727
onnx/decoder_model_merged_fp16.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:197b4f11700e089a8a21181d996901b9ee2def2da282ac4c8e51640b0eeaed51
3
- size 117708803
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:649799882ad5c14efc4bcf488a688b95feb81bb4adeceaf1d5bcda82015e31ab
3
+ size 117714397
onnx/decoder_model_merged_int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d141c4b8b120b9ad1e03c92d115d0bb6ebf416f7587822b905f2370942cf3955
3
+ size 59691033
onnx/decoder_model_merged_q4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65220b49b0382136dd69fc52af9ccda0f03ce0cd2e34310ad96307801d133737
3
+ size 149639679
onnx/decoder_model_merged_q4f16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81ac9ce89b0a34e1b1011921687d6329eaa0d7e51d043122361ab06f68d4fecd
3
+ size 81545948
onnx/decoder_model_merged_uint8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99925abd058460232cb5d7d5b456aeaa1e09af5536cf84c03072196e570629cb
3
+ size 59691062
onnx/decoder_model_q4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0183e93ad80b462d272d11a0cca4ce3bc10bcb4960808c5ea1f59dce1ff8d740
3
+ size 149382422
onnx/decoder_model_q4f16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:106815e3836a464fe07c0e7012f4cc6a8a8d0f5bdc5f71f27508cdcdb771e222
3
+ size 81119415
onnx/decoder_model_uint8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:528b25ed695ba6bfbc727d59bd7ce4f695f3963b553eee4d3c0d851fde3e6c69
3
+ size 191058563
onnx/decoder_with_past_model_bnb4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90899b6782fa219bd842f5cbec364e609b5810cd118d68f2d0c18ae54eec47a2
3
+ size 145947534
onnx/decoder_with_past_model_fp16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e4ba721f13066cd4a9a0a041e8d1b4bcc14f00be82bf7b78758469e1d470c79
3
+ size 110920712
onnx/decoder_with_past_model_int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f4d6800ac160ef617c00c2510aa89bc90cff3fb7b1db1887572dd86dd5db510
3
+ size 187809741
onnx/decoder_with_past_model_q4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0011cf667a7d1c0ea808df7bff2187ccf941aa82cc6a155c22e116093691f184
3
+ size 147323406
onnx/decoder_with_past_model_q4f16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27bfc0faabc3fe508599611c7bb08304319d63d1133613bb54d974167c7b57d3
3
+ size 79273983
onnx/decoder_with_past_model_uint8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cefc52736a9821d5813dab50bc6b23eb553f02667ca98afbde4eeb7e713ba27
3
+ size 187809764
onnx/encoder_model_bnb4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4665e1f43e9ecec39131b3afd5708f2554345363162e9b408622b57dd357c208
3
+ size 143787965
onnx/encoder_model_int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19f0e64f0552502871ec9775b2a17894a1b4b8263c201597cf0ba4bddc5f68ca
3
+ size 52407064
onnx/encoder_model_q4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b6081cd7fdf353c24f9b048790b0de0fd96ee8da952ca938a9c2616375994ee
3
+ size 144967325
onnx/encoder_model_q4f16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58c655ddb3b0fb784e13aa92bc25ae85952ac0fdd454fd5e2d8446ae53658c8e
3
+ size 77261857
onnx/encoder_model_uint8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e88ed1024c0b93451ed217a67355902d9878d529e04f39b728346a53630b0fda
3
+ size 52407083