Add Support For Robin-7b, Robin-13b, Robin-33b Model, a chatbot finetuned by HKUST

[hanningzhang]

Robin-7b is finetuned from LLaMA, achieving competitive performance on chitchat, commonsense reasoning, and instruction-following tasks.

Checks

• [x] I've run format.sh to lint the changes in this PR.
• [x] I've included any doc changes needed.
• [x] I've made sure the relevant tests are passing (if applicable).

We have tried this (Similar for 13b and 33b model):

python3 -m fastchat.model.apply_delta --base-model-path pinkmanlove/llama-7b --target-model-path ./model_weights/Full-Robin-7b-v2 --delta-path OptimalScale/robin-7b-v2-delta
python3 -m fastchat.serve.cli --model-path ./model_weights/Full-Robin-7b-v2 --max-new-tokens 1800