help wantednew model
Métricas do repositório
- Stars
- (4.990 stars)
- Métricas de merge de PR
- (Métricas PR pendentes)
Description
The model to consider.
I would like to request support for HyperCLOVAX-SEED-Omni-8B, a multimodal model developed by Naver CLOUD. This model is designed to handle interleaving text, image, and audio inputs/outputs.
HuggingFace Link: naver-hyperclovax/HyperCLOVAX-SEED-Omni-8B
Architecture Overview / Pipeline Stage:
roadmap
- HyperCLOVAX-SEED-Omni-8B implement on vllm https://github.com/vllm-project/vllm/pull/36590
- audio decoder implement on vllm-omni https://github.com/vllm-project/vllm-omni/pull/869/files
- vision decoder implement on vllm-omni https://github.com/vllm-project/vllm-omni/issues/631
The closest model vllm-omni already supports.
https://github.com/vllm-project/vllm-omni/issues/631
What's your difficulty of supporting the model you want?
Use case and motivation
No response
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.