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
45
Columbidae/CavesOfQwen3-exp16-Unhealed
Text Generation
•
31B
•
Updated
•
110
•
1
Columbidae/medgemma-27b-multimodal
Updated
•
237
Columbidae/Qwen3-16B-A3B-Base
16B
•
Updated
•
1.76k
Columbidae/Qwen3-16B-A3B-Base-Old-Archived
16B
•
Updated
•
2
Columbidae/Qwen3-16B-A3B-Tulu-Mini
Text Generation
•
16B
•
Updated
Columbidae/Qwen3-21B-Base-Zeroed
Text Generation
•
21B
•
Updated
•
14
•
1
Columbidae/Qwen3-21B-Base-Unzeroed
Text Generation
•
21B
•
Updated
•
2
Columbidae/Qwen3-30B-A3B-Base-Noisy
Text Generation
•
31B
•
Updated
•
10
Columbidae/Qwen3-30B-A3B-Noisy
Text Generation
•
31B
•
Updated
•
13
Columbidae/gemma-3-12b-it-text
12B
•
Updated
•
14
datasets
0
None public yet