Gabe Goodhart
gabegoodhart
AI & ML interests
None yet
Recent Activity
new activity
8 days ago
ibm-granite/granite-4.0-h-tiny:Fill-In-the-Middle (FIM) code completions
new activity
15 days ago
ibm-granite/granite-docling-258M:Why is granite-docling-258M so slow?
new activity
15 days ago
ibm-granite/granite-docling-258M:Which model are you using for the demo?
Organizations
Fill-In-the-Middle (FIM) code completions
1
#4 opened 10 days ago
by
cnmoro
Why is granite-docling-258M so slow?
🤝
1
18
#37 opened 22 days ago
by
hgarp-prozis
Which model are you using for the demo?
1
#41 opened 17 days ago
by
MelikaNLP
My review of granite-4.0-h-tiny
❤️
2
3
#2 opened 26 days ago
by
algorithm
How are these bounding boxes being generated on top of the demo images
1
#36 opened 22 days ago
by
hsuyab
ONNX Conversion Available - Performance Benchmarks & Implementation Guide
❤️
🚀
2
7
#32 opened 30 days ago
by
glamberson
High memory usage with mlx-lm
5
#1 opened 26 days ago
by
ironsmoke
VLLM Support
3
#1 opened 26 days ago
by
jtvino
Request for ONNX version
👀
🚀
2
5
#21 opened about 1 month ago
by
harisnaeem
llama.cpp
➕
2
4
#16 opened about 1 month ago
by
engrtipusultan
Single page image inference using plain tranformers not working
18
#10 opened about 1 month ago
by
zoldaten
Upload 2 files
2
#10 opened about 1 month ago
by
asbdu59823055981802112028
Upload 3 files
1
#9 opened about 1 month ago
by
asbdu59823055981802112028
Upload 3 files
1
#8 opened about 1 month ago
by
asbdu59823055981802112028
Create app.py
1
#7 opened about 2 months ago
by
23ucs565
Create App.py
1
#6 opened about 2 months ago
by
23ucs565
GGUF variant/ollama support
1
#2 opened about 2 months ago
by
ruddbanga7
GGUF support
❤️
4
18
#4 opened 2 months ago
by
RedEyed
feat: Add CPU support
#18 opened 2 months ago
by
gabegoodhart
