Make model type backwards compatible

[kunal-vaishnavi]

Description

This PR makes accessing the model type possible by reading from the GenAI config if the model object does not contain the type attribute. It also adds the chat and system templates for Qwen models.

Motivation and Context

This PR allows the examples to be backwards compatible with the published RCs for v0.6.0.

The Qwen chat template and Qwen system template were obtained from the following information.

>>> from transformers import AutoTokenizer
>>> tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-0.5B-Instruct", cache_dir="./cache_dir")
tokenizer_config.json: 100%|█████████████████████████████████████████████████████████████████████████████| 7.30k/7.30k [00:00<00:00, 9.64MB/s]
vocab.json: 100%|████████████████████████████████████████████████████████████████████████████████████████| 2.78M/2.78M [00:00<00:00, 16.5MB/s]
merges.txt: 100%|████████████████████████████████████████████████████████████████████████████████████████| 1.67M/1.67M [00:00<00:00, 15.6MB/s]
tokenizer.json: 100%|████████████████████████████████████████████████████████████████████████████████████| 7.03M/7.03M [00:00<00:00, 21.5MB/s]
>>> prompt = "Give me a short introduction to large language model."
>>> messages = [ {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."}, {"role": "user", "content": prompt} ]
>>> text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
>>> text
'<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n<|im_start|>user\nGive me a short introduction to large language model.<|im_end|>\n<|im_start|>assistant\n'

[MaanavD]

LGTM. Tested and works!

[apsonawane]

In model-chat.py in line 105 should we not have this line to modify prompt based on chat_template?
prompt = f'{chat_template.format(input=text)}'