llama_embeddings_lut8.mlmodelc/model.mil

program(1.3)
[buildInfo = dict<string, string>({{"coremlc-component-MIL", "3402.3.2"}, {"coremlc-version", "3402.4.1"}})]
{
    func main<ios18>(tensor<int32, [1, ?]> input_ids) [FlexibleShapeInformation = tuple<tuple<string, dict<string, tensor<int32, [?]>>>, tuple<string, dict<string, dict<string, tensor<int32, [?]>>>>>((("DefaultShapes", {{"input_ids", [1, 1]}}), ("EnumeratedShapes", {{"79ae981e", {{"input_ids", [1, 1]}}}, {"ed9b58c8", {{"input_ids", [1, 64]}}}})))] {
            int32 hidden_states_axis_0 = const()[name = string("hidden_states_axis_0"), val = int32(0)];
            int32 hidden_states_batch_dims_0 = const()[name = string("hidden_states_batch_dims_0"), val = int32(0)];
            bool hidden_states_validate_indices_0 = const()[name = string("hidden_states_validate_indices_0"), val = bool(false)];
            tensor<fp16, [128256, 2048]> embed_tokens_weight_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint8, [128256, 2048]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(64))), lut = tensor<fp16, [16032, 1, 256, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(262668416))))[name = string("embed_tokens_weight_to_fp16_palettized")];
            tensor<fp16, [1, ?, 2048]> hidden_states = gather(axis = hidden_states_axis_0, batch_dims = hidden_states_batch_dims_0, indices = input_ids, validate_indices = hidden_states_validate_indices_0, x = embed_tokens_weight_to_fp16_palettized)[name = string("hidden_states_cast_fp16")];
        } -> (hidden_states);
}