Wish to convert flan-t5 model to GGUF format

[niranjanakella]

Prerequisites

Please answer the following questions for yourself before submitting an issue.

• I am running the latest code. Development is very rapid so there are no tagged versions as of now.
• I carefully followed the README.md.
• I searched using keywords relevant to my issue to make sure that I am creating a new issue that is not already open (or closed).
• I reviewed the Discussions, and have a new bug or useful enhancement to share.

Expected Behavior

I was trying to convert google/flan-t5-large model to GGUF format using this colab.

I am importing the model this way

model_name = 'google/flan-t5-large'

model = AutoModelForSeq2SeqLM.from_pretrained(
    model_name,
    trust_remote_code=True,
    torch_dtype=torch.float16,
    device_map='cpu',
    offload_folder='offload',
    cache_dir=cache_dir
)

Current Behavior

I know that the current convert.py execution fails cause this type of model isn't supported
current error:

Loading model file models/pytorch_model.bin
Traceback (most recent call last):
  File "/content/llama.cpp/convert.py", line 1208, in <module>
    main()
  File "/content/llama.cpp/convert.py", line 1157, in main
    params = Params.load(model_plus)
  File "/content/llama.cpp/convert.py", line 288, in load
    params = Params.loadHFTransformerJson(model_plus.model, hf_config_path)
  File "/content/llama.cpp/convert.py", line 203, in loadHFTransformerJson
    n_embd           = config["hidden_size"]
KeyError: 'hidden_size'

Environment and Context

I am currently running all of this in a google colab notebook

• SDK version, e.g. for Linux:

Python 3.10.12
GNU Make 4.3
Built for x86_64-pc-linux-gnu
g++ (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0

I request help to accomplish this conversion. Can someone please suggest a method to convert this flan model to GGUF.

[BarfingLemurs]

No one has converted flan-t5 architecture to ggml, but if that happens, it will be in the ggml repository, see here: ggerganov/ggml#12

[github-actions]

This issue was closed because it has been inactive for 14 days since being marked as stale.