zhongwang lun

cnn365's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in hotdogs/qwen3.6-27b-fable5-lora about 8 hours ago

max_seq_length只有1024，这个训练感觉是负向优化了？有对比原始模型吗

1

#2 opened about 8 hours ago by

cnn365

New activity in lordx64/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled about 1 month ago

具体效果如何

#8 opened about 1 month ago by

cnn365

New activity in TeichAI/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill-GGUF 2 months ago

It does not work properly when running on VLLM.

1

#12 opened 2 months ago by

cnn365

New activity in Tongyi-Zhiwen/QwenLong-L1-32B about 1 year ago

Update README.md

#3 opened about 1 year ago by

cnn365