-
jeongseokoh/llama3.1_8b_sft_SPEED-28-BoS_HotpotQA_lower_freeze
Updated • 15 -
jeongseokoh/llama3.1_8b_sft_SPEED-24-BoS_HotpotQA_lower_freeze
Updated • 18 -
jeongseokoh/llama3.1_8b_sft_SPEED-20-BoS_HotpotQA_lower_freeze
Updated • 22 -
jeongseokoh/llama3.1_8b_sft_SPEED-16-BoS_HotpotQA_lower_freeze
Updated • 19
jeongseokoh
jeongseokoh
·
AI & ML interests
Large Language Models, Efficient LLM, Trustworthy AI
Recent Activity
upvoted a paper about 6 hours ago
Shallow Prefill, Deep Decoding: Efficient Long-Context Inference via Layer-Asymmetric KV Visibility updated a collection 1 day ago
SPEED submitted a paper 1 day ago
Shallow Prefill, Deep Decoding: Efficient Long-Context Inference via Layer-Asymmetric KV Visibility