moondream/moondream3-preview
Image-Text-to-Text
•
9B
•
Updated
•
10.1k
•
556
AI & ML interests
None defined yet.
Recent Activity
View all activity
Update BF16 weights + code to modelv2 shards (region LN + finetune support)
#32 opened about 6 hours ago
by
err805
Update BF16 weights + code to modelv2 shards (region LN + finetune support)
#32 opened about 6 hours ago
by
err805
vikhyatk
updated
a
model
15 days ago
err805
updated
a
dataset
21 days ago
err805
published
a
dataset
21 days ago
vikhyatk
published
a
dataset
25 days ago
vikhyatk
updated
a
dataset
25 days ago
vikhyatk
published
a
model
25 days ago
err805
updated
a
dataset
26 days ago
err805
published
a
dataset
26 days ago
err805
updated
a
dataset
26 days ago
err805
published
a
dataset
26 days ago
err805
updated
a
Space
about 1 month ago
err805
updated
a
model
about 2 months ago
err805
published
a
model
about 2 months ago
How to perform multi-image inference with Moondream3?
1
#29 opened 2 months ago
by
StrideH
err805
updated
a
model
2 months ago
Post
4241
Announcing RefCOCO-M, a refreshed RefCOCO with pixel-accurate masks and the problematic prompts removed.
moondream/refcoco-m
moondream/refcoco-m
Post
5229
Just released a preview of Moondream 3!
moondream/moondream3-preview
This is a 9B parameter, 2B active MoE VLM with state of the art visual reasoning capabilities.
More details in the release blog post: https://moondream.ai/blog/moondream-3-preview
This is a 9B parameter, 2B active MoE VLM with state of the art visual reasoning capabilities.
More details in the release blog post: https://moondream.ai/blog/moondream-3-preview
- 3 replies
Post
6206
🚨 New VQA + captioning dataset!
moondream/megalith-mdqa
Images from Megalith, captioned using Moondream, then transformed to short-form QA.
9M+ images, 6-10 QA pairs per image.
Images from Megalith, captioned using Moondream, then transformed to short-form QA.
9M+ images, 6-10 QA pairs per image.