[chat] refactor actor class

[ver217]

Motivation

Current actor class has method

ColossalAI/applications/Chat/coati/models/base/actor.py

Line 28 in b0ce5a1

def generate(

which makes strategy complex.

In strategy, it must check whether the model is Actor:

ColossalAI/applications/Chat/coati/trainer/strategies/base.py

Line 72 in a98af18

def prepare_model(model: nn.Module):

This makes developer confused.

Goal

Make Actor class clearer.

Roadmap

• Check whether it's training in forward() of Actor. If not, returns the original output of LM model.
• Extract generate() method of Actor to a function.
• Update naive experience maker.
• Refactor unwrap_model() method of Strategy, which should return the original model before prepare().
• Refactor get_base_model() function, which should return the base HF model. This should be called after being unwrapped.
• Refactor prepare() method of Strategy.