The models without suffixes use the default block size = 4.
AI & ML interests
Language Model, Diffusion Language Model
Recent Activity
models
22

JetLM/SDAR-30B-A3B-Chat-b8
Text Generation
•
31B
•
Updated

JetLM/SDAR-30B-A3B-Chat-b64
Text Generation
•
31B
•
Updated

JetLM/SDAR-30B-A3B-Chat-b16
Text Generation
•
31B
•
Updated

JetLM/SDAR-30B-A3B-Chat-b32
Text Generation
•
31B
•
Updated

JetLM/SDAR-8B-Chat-b64
Text Generation
•
8B
•
Updated

JetLM/SDAR-8B-Chat-b32
Text Generation
•
8B
•
Updated

JetLM/SDAR-8B-Chat-b16
Text Generation
•
8B
•
Updated

JetLM/SDAR-8B-Chat-b8
Text Generation
•
8B
•
Updated

JetLM/SDAR-4B-Chat-b64
Text Generation
•
4B
•
Updated

JetLM/SDAR-4B-Chat-b32
Text Generation
•
4B
•
Updated
datasets
0
None public yet