Qwen2.5 models with the tokenizers padded with extra unused special tokens to match the model embedding size. Workaround for various bugs.
Columba Labs
community
AI & ML interests
Birb make bots go brrr
Recent Activity
View all activity
models
63
Columbidae/apertus-12b-chatml-untrained
12B
•
Updated
•
178
Columbidae/Apertus-8B-2509-ChatML-trained-embeddings
Text Generation
•
4B
•
Updated
•
12
Columbidae/granite-4.0-h-small-half-slerp
32B
•
Updated
•
2
•
1
Columbidae/GLM-Air-Q4KM-Yarn-65k
Updated
•
33
Columbidae/GLM-Air-Q4KM-Yarn
Updated
•
25
Columbidae/Nemo-Base-Pruned-LP-Double
8B
•
Updated
•
7
Columbidae/Nemo-Base-Pruned-LP
8B
•
Updated
Columbidae/Nemo-Base-Pruned-Proj
7B
•
Updated
•
3
Columbidae/Nemo-Base-Pruned-S0
8B
•
Updated
•
1
Columbidae/Nemo-Base-Pruned-S0-Smaller
8B
•
Updated
•
2
datasets
0
None public yet