Incorporating `generation` tag to chat_template.json so that `return_assistant_tokens_mask` can work correctly with the tokenizer (https://github.com/huggingface/transformers/pull/30650/files). A self-contained test script is pasted below.
```python
from transformers import AutoProcessor
processor = AutoProcessor.from_pretrained("HuggingFaceM4/idefics2-8b")
# Define a chat histiry and use `apply_chat_template` to get correctly formatted prompt
# Each value in "content" has to be a list of dicts with types ("text", "image")
conversation = [
{
"role": "system",
"content": [
{"type": "text", "text": "You are a helpful assistant."},
]
},
{
"role": "user",
"content": [
{"type": "text", "text": "What is shown in this image?"},
{"type": "image"},
],
},
{
"role": "assistant",
"content": [
{"type": "text", "text": "This is a picture of a cat."},
]
}…
