mradermacher

/

llama-nemotron-embed-1b-v2-GGUF

like 0

Hi, I have a stupid question:

What is the best way of running this model?
I tried:

• llama_cpp (Llama class) ->
  llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'llama-embed'
• AutoModel.from_pretrained("mradermacher/llama-nemotron-embed-1b-v2-GGUF", gguf_file="llama-nemotron-embed-1b-v2.Q4_K_M.gguf") ->
  ValueError: GGUF model with architecture llama-embed is not supported yet.

My setup:
PyTorch version: 2.9.1+cu130
Transformers version: 4.57.3
llama_cpp_python version: 0.3.16

Thank you for your help in advance.
Pavel