Repository Issue Activity (beta)

#59 How to detect all objects in an image

#58 Inference speed (~14–15 TPS) with Molmo-7B-D-0924 (4-bit) and no improvement using vLLM

#57 Diagnostic Dataset for Probing Visual Hallucinations in VLMs

#56 Question Regarding Cap-F1 Evaluation Procedure

#53 Pixmo Clocks Code

#28 cap F1 dataset and prompts

#55 grad_norm is too large

#11 Dataset download issue

#21 Enforcing structured results (JSON)

#54 Regarding the number of output points

#48 Scaling Rate of the Image

#47 Does pixmo-points-eval have support in the evaluation scripts?

#50 [Question] Image mask in MultiModalPreprocessor

#52 Image resizing and point coordinates

#51 wandb logs?

#49 [Questions] Implementation on RoPE

#34 Confuse of param additional_vocab_size

#46 General maintanence of this repository?

#4 we can't download the allenai/pixmo-clocks dataset from the url. can you give me the correct url formate to download the dataset!

#39 Data download stuck

#43 About the Types of Prompts Used in Counting Training

#42 Question/Bug AttributeError: 'super' object has no attribute '_extract_past_from_model_output'

#41 Multi Image inference

#40 MetaCLIP variant

#37 Percentage of available images in pixmo