Save and Load sharded gptq checkpoint

[PanQiWei]

What does this pr do

This pr adds support to save and load sharded gptq checkpoint.

Currently implemented:

• save sharded gptq checkpoint by using save_quantized method:
  • remove the code that move model to CPU before save weights.
  • add max_shard_size argument (defauts to "10GB") to specify each weights file's max storage size.
  • add model_base_name argument (defaults to None) so that users can specify weights file's base name by themseves.

[CrazyBrick]

What does this pr do

This pr adds support to save and load sharded gptq checkpoint.

Currently implemented:

* save sharded gptq checkpoint by using `save_quantized` method:
  
  * remove the code that move model to CPU before save weights.
  * add `max_shard_size` argument (defauts to "10GB") to specify each weights file's max storage size.
  * add `model_base_name` argument (defaults to None) so that users can specify weights file's base name by themseves.

when can we use the updated code(loading sharded checkpoints which quantized by autogptq,such as Qwen-vl-chat-int4)

[TheBloke]

Ah yeah I forgot to test this for 0.5.0

I will give it a test today and then maybe it can be included in 0.5.1 @fxmarty ?

Actually never mind, I didn't notice it only included saving, not loading as well. I guess not much point saving if it can't load, as Transformers can already do both so may as well use that until AutoGPTQ can do both.

[fxmarty]

@TheBloke yeah I'm already spending more time than I should maintaining the repo. Let's wait if @PanQiWei comes back.

[LaaZa]

I happened to test this when I made a small sharded model to test the loading. Seemed to work fine, but I didn't do any comprehensive testing.

[ewof]

havent had an issue with this branch

[ewof]

the max file size for hf is 50gb