- Qwen3-30B-A3B-Instruct-2507-sft-fusang-swa=2k_sink=0
- Qwen3-30B-A3B-Instruct-2507-sft-fusang-swa=2k_sink=0_falayer=25_from0_step2_fadec
- Qwen3-30B-A3B-Instruct-2507-sft-fusang-swa=2k_sink=100_fadec
- Qwen3-30B-A3B-Instruct-2507-sft-fusang-swa=2k_sink=100_falayer=25_from0_step2_fadec
- Qwen3-30B-A3B-Thinking-2507-sft-fusang-swa=2k_sink=0
- Qwen3-30B-A3B-Thinking-2507-sft-fusang-swa=2k_sink=0_falayer=25_from0_step2
- Qwen3-30B-A3B-Thinking-2507-sft-fusang-swa=2k_sink=100
- Qwen3-30B-A3B-Thinking-2507-sft-fusang-swa=2k_sink=100_falayer=25_from0_step2_fadec
- Qwen3-30B-A3B-Thinking-2507-sft-fusang
- Qwen3-4B-Instruct-2507-sft-fusang-swa=2k_sink=0
- Qwen3-4B-Instruct-2507-sft-fusang-swa=2k_sink=0_fadec
- Qwen3-4B-Instruct-2507-sft-fusang-swa=2k_sink=0_falayer=13_from1_step4_fadec
- Qwen3-4B-Instruct-2507-sft-fusang-swa=2k_sink=0_falayer=25_from1_step2
- Qwen3-4B-Instruct-2507-sft-fusang-swa=2k_sink=0_falayer=7_from0_step8_fadec
- Qwen3-4B-Instruct-2507-sft-fusang-swa=2k_sink=10
- Qwen3-4B-Instruct-2507-sft-fusang-swa=2k_sink=100
- Qwen3-4B-Instruct-2507-sft-fusang-swa=2k_sink=100_falayer=25_from1_step2_fadec
- Qwen3-4B-Instruct-2507-sft-fusang
- Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=0
- Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=0_fadec
- Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=0_falayer=13_from0_step4_fadec
- Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=0_falayer=13_from1_step4
- Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=0_falayer=25_from0_step2_fadec
- Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=0_falayer=25_from1_step2
- Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=0_falayer=25_from1_step2_fadec
- Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=10
- Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=100
- Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=100_falayer=25_from1_step2_fadec
- Qwen3-4B-Thinking-2507-sft-fusang-swa=4k_sink=0_fadec
- Qwen3-4B-Thinking-2507-sft-fusang
-
5.73 kB
-
6.57 kB