David Wang

When will you upload the best model?

这个模型是1000分类的，但是做人脸哪有一千个分类啊

Do you have this plan ?

RuntimeError: Proxy error(ArgumentOutOfRangeException): Year, Month, and Day parameters describe an un-representable DateTime.

9

why?

你好，怎么让保存的模型能够分片，而不是保存一个几十G的大模型

2

你好，怎么让保存的模型能够分片，而不是保存一个几十G的大模型。 我看了一遍这里面的参数，但是发现是完整保存的，而不是分片的，这个有办法吗

想问一下，能不能加个重试的功能

Hello! I met some problems

2

when I put the pixel in **``` img_points = np.array(([449.45227 , 806.9983], [182.01617 , 577.92316]), dtype=np.double) ```** I get the world_position (-9.651732934228644, 0.8639356952913586, 0.0]) why the z axis is zero？...

It's so strange, accelerate==0.21.0, It said cannot import name 'LlavaLlamaForCausalLM' from 'llava.model' when I change accelerate==0.28.0. It worked

4

### Describe the issue Issue: Command: ``` python -m llava.serve.controller --host 0.0.0.0 --port 10000 ``` Log: ``` Traceback (most recent call last): File "/usr/local/lib/python3.10/runpy.py", line 187, in _run_module_as_main mod_name, mod_spec,...