moondream
/

moondream3-preview

Image-Text-to-Text

text-generation

Model card Files Files and versions

Resources

View closed (5)

Use nn.Linear instead of a custom linear function

#27 opened 4 days ago by

fix: preserve spatial_toks when reasoning=true

#26 opened 11 days ago by

CPU is forbidden ?

#24 opened 24 days ago by

Does this model only detect one type of target at a time?

#23 opened 26 days ago by

PDF support

#22 opened about 1 month ago by

chiragshahcompass

Dataset ?

#21 opened about 1 month ago by

What are the metrics/eval framework?

#20 opened about 1 month ago by

Perceptual Ambiguity and Visual-Verbal Coherence in Multimodal Models

#19 opened about 1 month ago by

Request: DOI

#17 opened about 1 month ago by

Any plan to release other size model

#16 opened about 1 month ago by

Quantization

#14 opened about 1 month ago by

Inconsistency between reasoning and answer

#13 opened about 1 month ago by

Local Installation Video and Testing - Step by Step

#12 opened about 1 month ago by

Inference failed: Torch not compiled with CUDA enabled

#11 opened about 1 month ago by

how to run ?

#10 opened about 1 month ago by

could support vllm or sglang?

#9 opened about 2 months ago by

training/ft guide

#7 opened about 2 months ago by

Degreaded point performance on some examples compared to the playground

#6 opened about 2 months ago by

New model not detecting the tap to type text

#5 opened about 2 months ago by

Amazing work !

#4 opened about 2 months ago by

Is there any official approach for fine-tuning the model for custom tasks ?

#3 opened about 2 months ago by

Struggles with images of chastity cages

#1 opened about 2 months ago by