Eval bug: Cannot convert nomic-embed-code to gguf

[rudiservo]

Name and Version

root@ff22031b6dce:/app# ./llama-cli --version
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
Device 0: NVIDIA GeForce GTX 1070, compute capability 6.1, VMM: yes
load_backend: loaded CUDA backend from /app/libggml-cuda.so
load_backend: loaded CPU backend from /app/libggml-cpu-sandybridge.so
version: 5237 (e1e8e09)
built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu

Operating systems

Linux

GGML backends

CUDA

Hardware

FX-8350, GTX1070

Models

nomic-embed-code

Problem description & steps to reproduce

trying to convert to GGUF to quantize and test

First Bad Commit

No response

Relevant log output

root@ff22031b6dce:/app# ./convert_hf_to_gguf.py /models/nomic-embed-code/ 
INFO:hf-to-gguf:Loading model: nomic-embed-code
INFO:hf-to-gguf:Model architecture: Qwen2Model
ERROR:hf-to-gguf:Model Qwen2Model is not supported

[CISC]

Only Qwen2ForCausalLM is currently supported, not Qwen2Model (decoder), but it looks like they are working on it?

[rudiservo]

@CISC thanks, I am really curious to try this out with a quantized model.