Update python API and reorg scripts

[zhenwei-intel]

Type of Change

API change

Description

• update init interface
• reorg scripts

instead of Automodel.from_pretrained, we change to following init:

model = Model()
model.init(model_name, weight_dtype="int4", compute_dtype="int8")
outputs = model.generate(inputs, streamer=streamer, max_new_tokens=300, do_sample=True)

Expected Behavior & Potential Risk

the expected behavior that triggered by this PR

How has this PR been tested?

how to reproduce the test (including hardware information)

Dependency Change?

any library dependency introduced or removed

[a32543254]

LGTM

[airMeng]

good to see we finally split scripts tools and python frontend!