Poster: A Preliminary Study of LLM Distillation Inference
Distillation-inference test flags Llama-3.2-3B models distilled from Qwen2.5-7B at TPR 1.0 and p=0.02.
1 stories, newest first · one card per story
Distillation-inference test flags Llama-3.2-3B models distilled from Qwen2.5-7B at TPR 1.0 and p=0.02.
Today 1.9K readers · 2.4K views · 368 reads · all time 111K views