Few Shot Learning
As discussion on : https://huggingface.co./meta-llama/Llama-3.2-11B-Vision-Instruct/discussions/43 that this model doesn't work reliably well with multiple images.
Is there any way we can achieve few shot prompting here to improve performance?
Not if the example involves images although I did use it for helping improve the model replies.
Please see example: https://github.com/meta-llama/llama-recipes/pull/698
Let me know if you have more Qs!
Hello @Sanyam , sorry for the late response as i was experimenting with single image usecases. But again, i wanted to check if few shot prompting with images i.e. multiimages on prompt will improve the response.
I went through your link but wasnot able to see fewshot example. Can you please state the file where i can find it.
However i did find few discussions on vLLM repo:
https://github.com/vllm-project/vllm/issues/8826
https://github.com/vllm-project/vllm/pull/9095
https://github.com/vllm-project/vllm/pull/9393
Where they have discussed and working to support multiimage prompt. Is this something llama 3.2 can handle since you recommended to use single image prompt.