Add Ghost 7B Alpha to models metadata

[lh0x00]

Ghost 7B Alpha is a large language model fine-tuned from Mistral 7B, with a size of 7 billion parameters. The model was developed with the goal of optimizing reasoning ability, multi-task knowledge and supporting tool usage. The model works well with the main trained and optimized languages being English and Vietnamese.

🤗 Card model: https://huggingface.co/ghost-x/ghost-7b-alpha
🌏 Official website: https://ghost-x.org/docs/models/ghost-7b-alpha
👻 Demo: https://ghost-x.org/docs/notebooks/playground-with-ghost-7b-alpha

Thanks for review!

[manyoso]

What is the difference between this one and the other Ghost 7b that we already have in the models3.json?

[lh0x00]

@manyoso Ghost 7B Alpha is final release and Ghost 7B v0.9.1 is early version, Ghost 7B Alpha was improved more than early version, model details here.