Delete logs/convert_float16.log with huggingface_hub
Browse files- logs/convert_float16.log +0 -73
logs/convert_float16.log
DELETED
|
@@ -1,73 +0,0 @@
|
|
| 1 |
-
[!] HF_TOKEN is not set. If model is public, you can pass --allow-no-token.
|
| 2 |
-
[+] Using existing model dir: /home/ubuntu/translategemma-4b-it
|
| 3 |
-
[+] ARCH: {'model_type': 'gemma3', 'architecture': 'Gemma3ForConditionalGeneration', 'vocab_size': 262208}
|
| 4 |
-
[+] Strategy 1: litert-torch native
|
| 5 |
-
[!] float16 support depends on converter/runtime build.
|
| 6 |
-
[+] Gemma3 builders available: ['build_model_1b', 'build_model_270m']
|
| 7 |
-
[+] Trying litert_torch.generative.examples.gemma3.gemma3.build_model_1b ...
|
| 8 |
-
[!] failed: 'NoneType' object has no attribute 'eval'
|
| 9 |
-
[+] Trying litert_torch.generative.examples.gemma3.gemma3.build_model_270m ...
|
| 10 |
-
[!] failed: 'NoneType' object has no attribute 'eval'
|
| 11 |
-
[!] Strategy 1 did not find a compatible builder
|
| 12 |
-
[+] Strategy 2: ai_edge_torch generic (wrapped logits-only)
|
| 13 |
-
[+] Loading HF model on CPU with dtype=torch.float16 ...
|
| 14 |
-
`torch_dtype` is deprecated! Use `dtype` instead!
|
| 15 |
-
|
| 16 |
-
Loading weights: 0%| | 0/883 [00:00<?, ?it/s]
|
| 17 |
-
Loading weights: 15%|███████████████▋ | 131/883 [00:00<00:00, 964.72it/s]
|
| 18 |
-
Loading weights: 26%|███████████████████████████▎ | 228/883 [00:00<00:00, 818.54it/s]
|
| 19 |
-
Loading weights: 35%|█████████████████████████████████████▏ | 310/883 [00:00<00:00, 656.66it/s]
|
| 20 |
-
Loading weights: 43%|█████████████████████████████████████████████▍ | 379/883 [00:00<00:00, 666.47it/s]
|
| 21 |
-
Loading weights: 51%|██████████████████████████████████████████████████████ | 450/883 [00:00<00:00, 679.41it/s]
|
| 22 |
-
Loading weights: 92%|████████████████████████████████████████████████████████████████████████████████████████████████▊ | 814/883 [00:00<00:00, 1573.63it/s]
|
| 23 |
-
Loading weights: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████| 883/883 [00:00<00:00, 1167.42it/s]
|
| 24 |
-
(00:00) [START] LiteRT-Torch Convert
|
| 25 |
-
(00:00) [START] LiteRT-Torch Convert > Torch Export: serving_default
|
| 26 |
-
(00:08) [START] LiteRT-Torch Convert > Torch Export: serving_default > ExportedProgram Run Decompositions
|
| 27 |
-
(00:27) [ DONE] LiteRT-Torch Convert > Torch Export: serving_default > ExportedProgram Run Decompositions (+00:18)
|
| 28 |
-
(00:27) [ DONE] LiteRT-Torch Convert > Torch Export: serving_default (+00:27)
|
| 29 |
-
(00:27) [START] LiteRT-Torch Convert > Run FX Passes
|
| 30 |
-
(00:28) [START] LiteRT-Torch Convert > Run FX Passes > ExportedProgram Run Decompositions
|
| 31 |
-
(00:28) [ DONE] LiteRT-Torch Convert > Run FX Passes > ExportedProgram Run Decompositions (+00:00)
|
| 32 |
-
(00:28) [ DONE] LiteRT-Torch Convert > Run FX Passes (+00:01)
|
| 33 |
-
(00:28) [START] LiteRT-Torch Convert > Lower to MLIR: serving_default
|
| 34 |
-
(00:28) [START] LiteRT-Torch Convert > Lower to MLIR: serving_default > ExportedProgram Run Decompositions
|
| 35 |
-
(00:46) [ DONE] LiteRT-Torch Convert > Lower to MLIR: serving_default > ExportedProgram Run Decompositions (+00:18)
|
| 36 |
-
(00:46) [START] LiteRT-Torch Convert > Lower to MLIR: serving_default > ExportedProgram Run Decompositions
|
| 37 |
-
(01:06) [ DONE] LiteRT-Torch Convert > Lower to MLIR: serving_default > ExportedProgram Run Decompositions (+00:19)
|
| 38 |
-
(01:06) [START] LiteRT-Torch Convert > Lower to MLIR: serving_default > Create MLIR Module
|
| 39 |
-
WARNING:jax._src.xla_bridge:An NVIDIA GPU may be present on this machine, but a CUDA-enabled jaxlib is not installed. Falling back to cpu.
|
| 40 |
-
(01:30) [ DONE] LiteRT-Torch Convert > Lower to MLIR: serving_default > Create MLIR Module (+00:23)
|
| 41 |
-
(01:30) [ DONE] LiteRT-Torch Convert > Lower to MLIR: serving_default (+01:01)
|
| 42 |
-
(01:30) [START] LiteRT-Torch Convert > Merge MLIR Modules
|
| 43 |
-
(01:30) [ DONE] LiteRT-Torch Convert > Merge MLIR Modules (+00:00)
|
| 44 |
-
(01:30) [START] LiteRT-Torch Convert > Run LiteRT Converter Passes
|
| 45 |
-
loc("__main__.strategy2_generic.<locals>.LogitsOnlyWrapper/transformers.models.gemma3.modeling_gemma3.Gemma3ForConditionalGeneration_model/transformers.models.gemma3.modeling_gemma3.Gemma3Model_model/transformers.models.gemma3.modeling_gemma3.Gemma3TextScaledWordEmbedding_embed_tokens;"("embedding"("/usr/local/lib/python3.12/dist-packages/torch/nn/modules/sparse.py":192:0))): error: failed to legalize operation 'tfl.embedding_lookup' that was explicitly marked illegal: %492 = "tfl.embedding_lookup"(%491, %274) : (tensor<128xi32>, tensor<262208x2560xf16>) -> tensor<128x2560xf16>
|
| 46 |
-
(03:48) [ FAIL] LiteRT-Torch Convert > Run LiteRT Converter Passes
|
| 47 |
-
(03:48) [ FAIL] LiteRT-Torch Convert
|
| 48 |
-
[!] Strategy 2 failed: Failed to run converter passes: /usr/local/lib/python3.12/dist-packages/torch/nn/modules/sparse.py:192:0: error: failed to legalize operation 'tfl.embedding_lookup' that was explicitly marked illegal: %492 = "tfl.embedding_lookup"(%491, %274) : (tensor<128xi32>, tensor<262208x2560xf16>) -> tensor<128x2560xf16>
|
| 49 |
-
|
| 50 |
-
Traceback (most recent call last):
|
| 51 |
-
File "/home/ubuntu/convert_translategemma_android.py", line 372, in main
|
| 52 |
-
tflite_file = strategy2_generic(
|
| 53 |
-
^^^^^^^^^^^^^^^^^^
|
| 54 |
-
File "/home/ubuntu/convert_translategemma_android.py", line 234, in strategy2_generic
|
| 55 |
-
edge_model = ai_edge_torch.convert(wrapped, (sample_ids,))
|
| 56 |
-
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 57 |
-
File "/usr/local/lib/python3.12/dist-packages/litert_torch/_convert/interface.py", line 323, in convert
|
| 58 |
-
return Converter().convert(
|
| 59 |
-
^^^^^^^^^^^^^^^^^^^^
|
| 60 |
-
File "/usr/local/lib/python3.12/dist-packages/litert_torch/_convert/interface.py", line 208, in convert
|
| 61 |
-
converted_model = core.convert_signatures(
|
| 62 |
-
^^^^^^^^^^^^^^^^^^^^^^^^
|
| 63 |
-
File "/usr/lib/python3.12/contextlib.py", line 81, in inner
|
| 64 |
-
return func(*args, **kwds)
|
| 65 |
-
^^^^^^^^^^^^^^^^^^^
|
| 66 |
-
File "/usr/local/lib/python3.12/dist-packages/litert_torch/_convert/core.py", line 158, in convert_signatures
|
| 67 |
-
exporter = litert_converter.exported_programs_to_flatbuffer(
|
| 68 |
-
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 69 |
-
File "/usr/local/lib/python3.12/dist-packages/litert_torch/_convert/litert_converter.py", line 189, in exported_programs_to_flatbuffer
|
| 70 |
-
converter_api_ext.run_convert_to_tfl_passes(
|
| 71 |
-
ValueError: Failed to run converter passes: /usr/local/lib/python3.12/dist-packages/torch/nn/modules/sparse.py:192:0: error: failed to legalize operation 'tfl.embedding_lookup' that was explicitly marked illegal: %492 = "tfl.embedding_lookup"(%491, %274) : (tensor<128xi32>, tensor<262208x2560xf16>) -> tensor<128x2560xf16>
|
| 72 |
-
|
| 73 |
-
[x] All conversion strategies failed
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|