Error when running inference on newly converted OpenELM MLX model, ValueError(f"Received parameters not in model: {extras}.") about mlx-examples HOT 1 CLOSED

Update: During conversion, edited utils.py at line 688 to point to local tokenizer and now inference works.

  tokenizer.save_pretrained("/Users/USER/Downloads/Raw Downloads/mlx-examples-main-2/llms/mlx_lm/Llama-2-7b-hf")

OUTPUT:

None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used.
==========
Prompt: Tell me a story about Python programming
, and I'll tell you a thing or two about my life.....

However, using the model through LLMEvaluator gives the following error.

libc++abi: terminating due to uncaught exception of type std::invalid_argument: [matmul] Last dimension of first input with shape (1,916,2048) must match second to last dimension of second input with shape (256,32000)

How I used it..

let modelConfiguration = ModelConfiguration(
id: "Paramstr/MLX_OpenELM_1.1b_UiRev_finetuned_V3",
overrideTokenizer: "meta-llama/Llama-2-7b-hf"
)

from mlx-examples.