ZizhengZhan's picture

ZizhengZhan

Anditty

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 2 days ago

WebCompass: Towards Multimodal Web Coding Evaluation for Code Language Models

reacted to AdinaY's post with 👍 8 months ago

KAT-V1 🔥 a LLM that tackles overthinking by switching between reasoning and direct answers, by Kuaishou. https://huggingface.co/Kwaipilot/KAT-V1-40B ✨ 40B ✨ Step-SRPO: smarter reasoning control via RL ✨ MTP + Distillation: efficient training, lower cost

upvoted a paper 9 months ago

KAT-V1: Kwai-AutoThink Technical Report

View all activity

Organizations

New activity in Kwaipilot/KwaiCoder-23B-A4B-v1 about 1 year ago

prompt format in code completion

#1 opened about 1 year ago by

New activity in codellama/codellama-playground over 2 years ago

Should add <bos_id> token with infilling

#11 opened over 2 years ago by

New activity in bigcode/starcoder over 2 years ago

starcoder uses Megatron-LM?

#27 opened almost 3 years ago by