Steve Li's picture

Steve Li

CHNtentes

·

CHNtentes

AI & ML interests

None yet

Recent Activity

new activity about 23 hours ago

deepseek-ai/DeepSeek-V4-Pro: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

new activity about 24 hours ago

deepseek-ai/DeepSeek-V4-Flash:May I ask if there is a deployment document?

new activity 2 days ago

Qwen/Qwen3.6-27B-FP8:Parameter model.layers.15.mlp.gate_gate_up_proj.weight_scale_inv not found in params_dict

View all activity

Organizations

None yet

models 3

CHNtentes/Nanbeige4-3B-Thinking-2511-FP8-DYNAMIC

4B • Updated Jan 4 • 2

CHNtentes/Kimi-Linear

Updated Dec 18, 2025

CHNtentes/Qwen3-4B-Thinking-2507_Meow

Text Generation • 4B • Updated Oct 12, 2025 • 9 • 2

datasets 0

None public yet