Xingkai Yu

GeeeekExplorer's activity

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

New activity in deepseek-ai/DeepSeek-V4-Flash-DSpark 24 days ago

Update README.md to add vLLM snippet

1

#2 opened 24 days ago by

xianbao

New activity in deepseek-ai/DeepSeek-V4-Pro-DSpark 24 days ago

Update README.md to include vLLM snippet

#4 opened 24 days ago by

xianbao

published 2 models about 1 month ago

deepseek-ai/DeepSeek-V4-Pro-DSpark

Text Generation • 1.7T • Updated 24 days ago • 42.1k • 516

deepseek-ai/DeepSeek-V4-Flash-DSpark

Text Generation • 165B • Updated 24 days ago • 394k • 220

updated 2 models about 1 month ago

deepseek-ai/DeepSeek-V4-Pro-DSpark

Text Generation • 1.7T • Updated 24 days ago • 42.1k • 516

deepseek-ai/DeepSeek-V4-Flash-DSpark

Text Generation • 165B • Updated 24 days ago • 394k • 220

updated a collection about 1 month ago

DeepSeek-V4

Collection

6 items • Updated about 1 month ago • 756

updated 2 models about 2 months ago

deepseek-ai/DeepSeek-V4-Flash

Text Generation • 158B • Updated Jun 22 • 3.11M • • 1.84k

deepseek-ai/DeepSeek-V4-Pro

Text Generation • 1.6T • Updated Jun 22 • 1.65M • • 5.33k

updated 2 models 3 months ago

deepseek-ai/DeepSeek-V4-Flash-Base

292B • Updated Apr 27 • 205k • 283

deepseek-ai/DeepSeek-V4-Pro-Base

1.6T • Updated Apr 27 • 46.1k • 320

New activity in deepseek-ai/DeepSeek-V4-Pro 3 months ago

有一处明显笔误

👀 6

4

#109 opened 3 months ago by

chenzihong

所以我猜是混合精度加模型太大导致暂时还没有量化的模型出来

6

#96 opened 3 months ago by

lzm1066258

Not able to run deepseek v4 pro using transformers in Google Collab

2

#95 opened 3 months ago by

chandu8848

How to convert fp8 on Hopper?

1

#67 opened 3 months ago by

whybeyoung

Is there a mismatch between tech report and config.json of indexer top k ?

2

#20 opened 3 months ago by

FrankYan0824

Update index_topk to 1024

1

#25 opened 3 months ago by

FrankYan0824

upvoted a collection 3 months ago

DeepSeek-V4

Collection

6 items • Updated about 1 month ago • 756

updated a model 8 months ago

deepseek-ai/DeepSeek-V3.2-Exp

Text Generation • 685B • Updated Nov 18, 2025 • 291k • • 992