"Error loading llama server" when using a T5ForConditionalGeneration architucture model, converted to GGUF format

### What is the issue? With the help of https://huggingface.co/spaces/ggml-org/gguf-my-repo I made the https://huggingface.co/iG8R/t5_translate_en_ru_zh_large_1024_v2-Q8_0-GGUF model which was successfully imported into `ollama`. But when I try to use it, I always get the following error, while all other models work almost perfectly: ``` GGML_ASSERT: C:\a\ollama\ollama\llm\llama.cpp\src\llama.cpp:14882: strcmp(embd->name, "result_norm") == 0 time=2024-07-26T23:33:10.669+03:00 level=INFO source=server.go:617 msg="waiting for server to become available" status="llm server error" time=2024-07-26T23:33:10.934+03:00 level=ERROR source=sched.go:443 msg="error loading llama server" error="llama runner process has terminated: exit status 0xc0000409" [GIN] 2024/07/26 - 23:33:10 | 500 | 9.3372066s | 127.0.0.1 | POST "/v1/chat/completions" ``` Here is the full log: ``` time=2024-07-26T23:33:09.450+03:00 level=WARN source=memory.go:115 msg="model missing blk.0 layer size" time=2024-07-26T23:33:09.451+03:00 level=INFO source=sched.go:701 msg="new model will fit in available VRAM in single GPU, loading" model=H:\OllamaModels\blobs\sha256-cca50b43a8d0071238d9cb22864768dec5a8146f0b9969b83e69a076e267b17e gpu=GPU-60a344b3-0290-00b9-ed05-6b799407d228 parallel=4 available=10883338240 required="702.5 MiB" time=2024-07-26T23:33:09.451+03:00 level=WARN source=memory.go:115 msg="model missing blk.0 layer size" time=2024-07-26T23:33:09.451+03:00 level=INFO source=memory.go:309 msg="offload to cuda" layers.requested=-1 layers.model=25 layers.offload=25 layers.split="" memory.available="[10.1 GiB]" memory.required.full="702.5 MiB" memory.required.partial="702.5 MiB" memory.required.kv="48.0 MiB" memory.required.allocations="[702.5 MiB]" memory.weights.total="48.0 MiB" memory.weights.repeating="17179869184.0 GiB" memory.weights.nonrepeating="67.5 MiB" memory.graph.full="128.0 MiB" memory.graph.partial="128.0 MiB" time=2024-07-26T23:33:09.455+03:00 level=INFO source=server.go:383 m…