Please help add SeaLLM-7B-v2 with 7.54 on MT-bench on the leaderboard

Nobody has claimed this yet.

Hi Lmsys team,

We released [SeaLLM-7B-v2](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2) last week - a multilingual model that achieves **7.54** on the English MT-bench.

**Can you please check and verify the results and add our model to the leaderboard!**

## Generation and GPT-4 ratings files:

[https://huggingface.co/SeaLLMs/SeaLLM-7B-v2/tree/main/evaluation/mt_bench](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2/tree/main/evaluation/mt_bench)

Please find the files in the link above.

## Steps to reproduce the results:

1. Add the format to [conversations.py](https://github.com/lm-sys/FastChat/blob/main/fastchat/conversation.py)

```python
# Seallm
register_conv_template(
Conversation(
name="seallm",
system_template="""<|im_start|>system
{system_message}""",
system_message="""You are a helpful, intelligent and safe assistant.""",
roles=("<|im_start|>user", "<|im_start|>assistant"),
sep_style=SeparatorStyle.CHATML,
sep="",
stop_token_ids=[0, 1],
)
)

```

2. Add the following to [model_adapter.py](https://github.com/lm-sys/FastChat/blob/main/fastchat/model/model_adapter.py)

```python

class SeaLLMAdapter(BaseModelAdapter):
"""The model adapter for SeaLLMAdapter"""

use_fast_tokenizer = False

def match(self, model_path: str):
return "sea" in model_path.lower()

def get_default_conv_template(self, model_path: str) -> Conversation:
return get_conv_template("seallm")
```

Start with fastchat/conversation.py and fastchat/model/model_adapter.py, following the SeaLLM conversation template and adapter shown in the issue. Review the linked SeaLLM generation and GPT-4 ratings files and the existing leaderboard evaluation flow. Done means SeaLLM-7B-v2 is supported and its reported MT-bench result has been checked for leaderboard inclusion.

Written by the indexing model from the issue text.