Incorrect Output or Generating Random Characters

[Little0o0]

I downloaded the 1bitLLM/bitnet_b1_58-large and 1bitLLM/bitnet_b1_58-3B models. When I run the inference commands, the model does not error out but produces incorrect outputs.

python setup_env.py -md models/bitnet_b1_58-3B -q tl1
python run_inference.py -m models/bitnet_b1_58-3B/ggml-model-tl1.gguf -p "You are a helpful assistant" -cnv

When using the i2_s quantization in the above commands, it repeats random characters.

My platform is macOS (Apple M2 Pro)

Could you please help me resolve this?