Vadim Smirnov

ukint-vs

·

https://ukint-vs.github.io

AI & ML interests

None yet

Recent Activity

liked a dataset 6 days ago

HuggingFaceCode/stack-v3-train

liked a model 6 days ago

Nanbeige/Nanbeige4.2-3B-Base

liked a model 6 days ago

ukint-vs/Nanbeige4.2-3B-CoreAI

View all activity

Organizations

New activity in mlx-community/gemma-4-e2b-4bit 4 months ago

⚠️ Existing MLX quantized Gemma 4 models (mlx-community, unsloth) produce garbage output due to quantizing PLE (Per-Layer Embedding) layers.

#1 opened 4 months ago by