vicuna-7b fastchat.serve.cli stops loading checkpoint shards in my google colab

I've been trying to get fastchat to work many times but i always get stuck here. I'm using a google colab with python 3.10.12 and i've followed the installation instructions.
i'm trying to run this:
!python -m fastchat.serve.cli --model-path lmsys/vicuna-7b-v1.3

and here's the output:
023-06-24 16:34:14.704392: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
Loading checkpoint shards: 50% 1/2 [01:23<01:23, 83.38s/it]^C

(i did not stop it)
not sure if it has to deal with trensorRT.
I've already tried with vicuna-7b-v1.3, vicuna-13b-v1.3 and fastchat-t5-3b-v1.0 and they all end up with this output.
I've also tried with only using cpu and still the same.

Thanks

Reproduce the reported command, python -m fastchat.serve.cli --model-path lmsys/vicuna-7b-v1.3, in the stated Google Colab and Python 3.10.12 environment. Start from the fastchat.serve.cli entry point and determine whether the TensorRT warning or checkpoint loading is responsible; done means identifying the cause and confirming that the model loads successfully.