Hugging Face's logo
spooner's picture
3 2 11

spooner

spooner2
Mi6paulino's profile picture jeiku's profile picture 21world's profile picture
·

AI & ML interests

None yet

Recent Activity

liked a model 29 days ago
Disty0/Z-Image-Turbo-SDNQ-uint4-svd-r32
reacted to mitkox's post with 🔥 5 months ago
I got 370 tokens/sec of Qwen3-30B-A3B 2507 on my desktop Z8 GPU workstation. My target is 400 t/s, and the last 10 % always tastes like victory!
reacted to eaddario's post with 🚀 6 months ago
Layer-wise and Pruned versions of Qwen/Qwen3-30B-A3B * Tesor-wise: https://huggingface.co/eaddario/Qwen3-30B-A3B-GGUF * Pruned: https://huggingface.co/eaddario/Qwen3-30B-A3B-pruned-GGUF Even though the Perplexity scores of the pruned version are 3 times higher, the ARC, HellaSwag, MMLU, Truthful QA and WinoGrande scores are holding remarkably well, considering two layers were removed (5 and 39). This seems to support Xin Men et al conclusions in ShortGPT: Layers in Large Language Models are More Redundant Than You Expect (2403.03853) Results summary in the model's card and test results in the ./scores directory. Questions/feedback is always welcomed.
View all activity

Organizations

None yet