Vishaal Udandarao

Hi, could you please let me know if/when you are planning to release the code for CLIP-Adapter on Imagenet?

add lat-long-identify eval

1

# Thank you for contributing an eval! ♥️ 🚨 Please make sure your PR follows these guidelines, __failure to follow the guidelines below will result in the PR being closed...

Multi-image inputs to the model

1

Hi, I was wondering if it is possible to prompt the model with more than one image input since in the implementation the incorporation of the visual tokens is a...

Hi, is it possible to get the tokenwise log-likelihood scores of different outputs from the model? The use-case would be something like: Given an interleaved image/text input and a list...

Added cache_dir argument for downloading model to a specific directory

4

The current code only supports downloading to the `.checkpoints` directory. This PR adds functionality to download model checkpoints to a specific directory with the `cache_dir` argument to `models.imagebind_model.imagebind_huge()`.

[Question] Getting output likelihood scores from the model

10

### Question Hi, is it possible to get the tokenwise log-likelihood scores of different outputs from the model? The use-case would be something like: Given an interleaved image/text input and...

Computing output likelihoods with the InstructBLIP model

2

Hi, is it possible to get the tokenwise log-likelihood scores of different outputs from the InstructBLIP model? The use-case would be something like: Given an interleaved image/text input and a...

Confusion regarding model versions?

1

Hi, with release of the new [MIMIC-IT paper](https://arxiv.org/abs/2306.05425)---I am bit confused regarding the different model versions you have. Is the model on [huggingface](https://huggingface.co/luodian/otter-9b-hf) the same as the ones for which...

Internal Server Error while searching by text

2

Hi, I am trying to search the hosted clip-retrieval backend index by text and end up getting an internal server error. Here is the code I used: ```python from clip_retrieval.clip_client...