-
First of all thank you for the amazing work. I just checked out v0.3.1 which obviously includes the breaking changes from v0.3.0 and noticed that the whole interpretability part got removed. Why is th…
-
Hi ! Thanks to opensource the Colpali ! ^.^
But here is a little question with when i use the [https://github.com/illuin-tech/colpali/blob/9413418c110da49b25ac2dae2c32b8fc067ff332/scripts/infer/run_i…
-
Hey @ManuelFay and team, great work, the colpali model works very well on image retrieval.
I wanted to know how to create a quantized version of this model? Any instrucitons or scripts?
-
Hi.
The current codebase provided for training/finetuning `Colapli1.2` based on hard negatives is not executable and raises multiple errors along the way:
running
`USE_LOCAL_DATASET=0 python scri…
-
Multi-vector MaxSim is increasingly important and we have optimizations for float cell precision, but I think we should also consider optimize for int8 with hamming as it approximates the dotproduct f…
-
Firstly, thanks for this cool work combining Paligemma and Colbert!
Given a PDF file
When I try the same PDF using the HF demo app at: https://huggingface.co/spaces/manu/ColPali-demo
And I try t…
-
### System Info
Problem is on the model hub
### Who can help?
@stevhliu
### Information
- [X] The official example scripts
- [ ] My own modified scripts
### Tasks
- [ ] An offic…
-
https://github.com/illuin-tech/colpali/blob/ad93aeb0d683a1ba621325834817441d9de5a780/colpali_engine/interpretability/gen_interpretability_plots.py#L86
`attention_map_normalized` is a torch `Bfloat1…
-
I'm trying to give an input image and a prompt/question related to the image, and I want to get the relevant answer from ColPali model. But I'm not able to implement this . When I try
> model.gene…
-
Sudden change in the code structured made my code break.
It is a great library for RAG. Kindly maintain the structure and updates without code breaks as we are planning for a extensive set of exper…