Add support of Huggince Face transformers

[bact]

Hugging Face's transformers is a popular Python library for model training and inference.

It may be possible to infer some information from the uses of well-known functions and classes like AutoModelForCausalLM and AutoTokenizer.

For example, from the code

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Qwen/Qwen3-30B-A3B-Thinking-2507"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

We can infer that this model uses tokenizer from "Qwen/Qwen3-30B-A3B-Thinking-2507".

More information could be obtain from tokenizer_config.json and config.json inside model repo on Hugging Face.