libin

daniellibin's activity

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

New activity in deepseek-ai/DeepSeek-R1-Distill-Qwen-32B about 1 year ago

Generate crashed by repeatedly generating <think>

1

#35 opened about 1 year ago by

qpz

New activity in deepseek-ai/DeepSeek-R1 about 1 year ago

qwen32B蒸馏模型，长度>8k时，预测一定比例乱码，出现<think><think><think><think><think><think>

5

#44 opened about 1 year ago by

daniellibin

qwen32B蒸馏模型，长度>8k时，预测一定比例乱码，出现<think><think><think><think><think><think>

5

#44 opened about 1 year ago by

daniellibin

qwen32B蒸馏模型，长度>8k时，预测一定比例乱码，出现<think><think><think><think><think><think>

5

#44 opened about 1 year ago by

daniellibin