Federico Cocchi comments

Results 5 comments of


                                            Federico Cocchi

Is there any way to combine these models to Ollama?

Hi @lichenxi-cat and @hybra, thank you for your interest in our work. At the moment, we don't have a specific timeline for integrating the LLaVA-MORE weights into the Ollama format....

Using multimodal processor vs. separate tokenizer and image_processor

Hi @joris-sense , thank you for your interest in our project! To solve the problem, you should modify the `TransformersVision `class, within the `outlines `repo so that you can handle...

Evaluation result with officially released weights.

Hi @YuchenLiu98, thank you once again for your interest in our LLaVA-MORE project. For evaluation purposes, we use the `lmms-eval` library (https://github.com/EvolvingLMMs-Lab/lmms-eval), in which we integrate our models. Regarding the...

tokenization mismatch

Hi everyone, thank you for your interest in our project !!! We have conduct some tests to better understand the differences in behavior between the code we're running and the...

tokenization mismatch

@waybarrios the problem of mismatch is not in the model weights, but in the tokenizer.