[New Model]: ll-13/SkySenseGPT-7B-CLIP-ViT (GeoChatLlamaForCausalLM architecture)

[ppatel-eng]

The model to consider.

https://huggingface.co/ll-13/SkySenseGPT-7B-CLIP-ViT

The closest model vllm already supports.

None with the same architecture, perhaps a Llama model like meta-llama/Meta-Llama-3.1-8B

What's your difficulty of supporting the model you want?

New architecture: GeoChatLlamaForCausalLM

Before submitting a new issue...

• Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.