moondream/gsm8k
Viewer • Updated • 17.6k • 137
AI & ML interests
None defined yet.
Recent Activity
err805
updated a
dataset 5 days ago
err805
published a
dataset 5 days ago
vikhyatk
updated a
model 14 days ago
vikhyatk
published a
model 14 days ago
Always output inaccurate results
2
#34 opened about 2 months ago
by 
Gureumi
Fix runtime buffers after load
#37 opened 23 days ago
by 
err805
Fix runtime buffers after load
1
#36 opened 23 days ago
by err805
Fix runtime buffers after load
#37 opened 23 days ago
by err805
Fix runtime buffers after load
1
#35 opened 23 days ago
by err805
err805
updated a
model 23 days ago
err805
updated a
dataset 25 days ago
err805
published a
dataset 25 days ago
err805
updated a
dataset 25 days ago
err805
published a
dataset 25 days ago
err805
updated a
dataset 25 days ago
err805
published a
dataset 25 days ago
err805
authored a
paper 26 days ago
Post
4929
Announcing RefCOCO-M, a refreshed RefCOCO with pixel-accurate masks and the problematic prompts removed.
moondream/refcoco-m
moondream/refcoco-m
Post
5954
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
6233
🚨 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.