SDAR-VL JetLM/SDAR-VL-Instruct-4B 5B • Updated 16 days ago • 13 JetLM/SDAR-VL-Instruct-8B 9B • Updated 16 days ago • 17 JetLM/SDAR-VL-Think-4B 5B • Updated 16 days ago • 15 JetLM/SDAR-VL-Think-8B Updated 16 days ago
SDAR The models without suffixes use the default block size = 4. JetLM/SDAR-1.7B-Chat Text Generation • 2B • Updated Oct 21 • 660 • 7 JetLM/SDAR-4B-Chat Text Generation • 4B • Updated Oct 21 • 155 • 2 JetLM/SDAR-8B-Chat Text Generation • 8B • Updated Oct 21 • 240 • 3 JetLM/SDAR-30B-A3B-Chat Text Generation • 31B • Updated Oct 21 • 17 • 2
Nirvana Nirvana: A Specialized Generalist Model With Task-Aware Memory Mechanism YuhuaJiang/Nirvana-pro 2B • Updated Oct 13 • 9 • 3 YuhuaJiang/Nirvana-simple 2B • Updated Oct 13 • 5 • 2 YuhuaJiang/Nirvana 2B • Updated Oct 13 • 6 • 2
SDAR-VL JetLM/SDAR-VL-Instruct-4B 5B • Updated 16 days ago • 13 JetLM/SDAR-VL-Instruct-8B 9B • Updated 16 days ago • 17 JetLM/SDAR-VL-Think-4B 5B • Updated 16 days ago • 15 JetLM/SDAR-VL-Think-8B Updated 16 days ago
Nirvana Nirvana: A Specialized Generalist Model With Task-Aware Memory Mechanism YuhuaJiang/Nirvana-pro 2B • Updated Oct 13 • 9 • 3 YuhuaJiang/Nirvana-simple 2B • Updated Oct 13 • 5 • 2 YuhuaJiang/Nirvana 2B • Updated Oct 13 • 6 • 2
SDAR The models without suffixes use the default block size = 4. JetLM/SDAR-1.7B-Chat Text Generation • 2B • Updated Oct 21 • 660 • 7 JetLM/SDAR-4B-Chat Text Generation • 4B • Updated Oct 21 • 155 • 2 JetLM/SDAR-8B-Chat Text Generation • 8B • Updated Oct 21 • 240 • 3 JetLM/SDAR-30B-A3B-Chat Text Generation • 31B • Updated Oct 21 • 17 • 2