luchangli03

luchangli03's activity

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

liked a model 5 days ago

lightseekorg/kimi-k2.5-eagle3

3B • Updated 3 days ago • 3.66k • 1

New activity in AQ-MedAI/Kimi-K25-eagle3 9 days ago

Can you reduce the kv head num of this model? "num_key_value_heads": 64, which requies a lots of kv cache

2

#1 opened 10 days ago by

luchangli03

liked a model 10 days ago

AQ-MedAI/Kimi-K25-eagle3

1B • Updated about 17 hours ago • 1.74k • 6

New activity in jerryzh168/Kimi-K2-Thinking-FP8 30 days ago

Can you provide the code that convert the int4 weight to fp8? thanks

#2 opened 30 days ago by

luchangli03

New activity in chutesai/DeepSeek-V3.1-Terminus-NextN 4 months ago

what's the difference between this nextn and self contained MTP model in DeepSeek-V3.1-Terminus?

#1 opened 4 months ago by

luchangli03

liked a Space about 1 year ago

Running

3.74k

The Ultra-Scale Playbook

🌌

3.74k

The ultimate guide to training LLM on large GPU Clusters