opt-125M-awq onnx model

[AmosLewis]

command.log

PYTHONPATH=/home/chi/src/torch-mlir/build/tools/torch-mlir/python_packages/torch_mlir python runmodel.py  --todtype default --mode onnx --outfileprefix opt-125M-awq 1> model-run.log 2>&1
PYTHONPATH=/home/chi/src/torch-mlir/build/tools/torch-mlir/python_packages/torch_mlir python -m torch_mlir.tools.import_onnx /home/chi/src/SHARK-TestSuite/e2eshark/onnx/models/opt-125M-awq/model.onnx -o opt-125M-awq.default.torch-onnx.mlir 1> onnx-import.log 2>&1
/home/chi/src/torch-mlir/build/bin/torch-mlir-opt -pass-pipeline='builtin.module(func.func(convert-torch-onnx-to-torch),torch-lower-to-backend-contract,func.func(cse,canonicalize),torch-backend-to-linalg-on-tensors-backend-pipeline)' opt-125M-awq.default.torch-onnx.mlir > opt-125M-awq.default.onnx.linalg.mlir 2>torch-mlir.log

torch-mlir.log

opt-125M-awq.default.torch-onnx.mlir:1123:13: error: 'tensor.expand_shape' op expected number of static shape dims to be equal to the output rank (3) but found 0 inputs instead
    %1119 = torch.operator "onnx.Gather"(%0, %1113) : (!torch.vtensor<[50272,768],f32>, !torch.vtensor<[?,?],si64>) -> !torch.vtensor<[?,?,768],f32> 
            ^
opt-125M-awq.default.torch-onnx.mlir:1123:13: note: see current operation: %1049 = "tensor.expand_shape"(%1046) <{reassociation = [[0, 1], [2]], static_output_shape = array<i64>}> : (tensor<?x768xf32>) -> tensor<?x?x768xf32>

Related issues: nod-ai/SHARK-ModelDev#242

[AmosLewis]

New iree issue after gather : iree-org/iree#17806