zhaoxi

qingshuiL's activity

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

New activity in kshitijthakkar/deepseek-v4-mini-1B-init 3 months ago

The pretraining loss convergence is not ideal.

6

#1 opened 3 months ago by

qingshuiL

New activity in google/siglip2-base-patch16-224 about 1 year ago

The accuracy on the ImageNet dataset is low

👍 1

1

#13 opened about 1 year ago by

qingshuiL

New activity in deepseek-ai/DeepSeek-V3-Base over 1 year ago

这东西cpu能跑不

8

#46 opened over 1 year ago by

helloquark

有人跑成功了吗， 用的什么配置跑的

6

#58 opened over 1 year ago by

xl343

New activity in deepseek-ai/DeepSeek-V3 over 1 year ago

Converted bf16 Model on Hugging Face

🤝 3

2

#5 opened over 1 year ago by

OpenSourceRonin