Not able to convert tiny lamma model to tflite with the latest nightly builds.

[akshatshah17]

Description of the bug:

Getting Segmentation fault while converting using the latest nightly builds. (28ce35b)
Weights are cloned from here https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0

2024-09-17 13:04:18.061978: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable TF_ENABLE_ONEDNN_OPTS=0.
2024-09-17 13:04:18.083295: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:477] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
E0000 00:00:1726558458.128374 2369696 cuda_dnn.cc:8321] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1726558458.140542 2369696 cuda_blas.cc:1418] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
2024-09-17 13:04:18.172989: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
Segmentation fault

Actual vs expected behavior:

No response

Any other information you'd like to share?

No response

[haozha111]

hi, could you try today's nightly build?
pip install ai-edge-torch-nightly==0.3.0.dev20240918
pip install transformers

and then run https://github.com/google-ai-edge/ai-edge-torch/blob/main/ai_edge_torch/generative/examples/tiny_llama/verify.py

I tested it and i'm seeing it's working.