Explore projects
-
back up of my graduation project, a new block scheduler for Crail.
Updated -
Updated
-
Updated
-
Updated
-
-
zhijun wang / Megatron-DeepSpeed
Apache License 2.0Ongoing research training transformer language models at scale, including: BERT & GPT-2
Updated -
zhang chaoyue / lottery
MIT LicenseUpdated -
王思齐 / dotoj-njuise
GNU General Public License v3.0 onlyUpdated -
Updated
-
LDM / TBPLaS Demo
BSD 3-Clause "New" or "Revised" LicenseUpdated -
zhang chaoyue / doop-zcy
Universal Permissive License v1.0Updated -
zhijun wang / LLaMA-Factory
Apache License 2.0Easy-to-use LLM fine-tuning framework (LLaMA, BLOOM, Mistral, Baichuan, Qwen, ChatGLM)
Updated -
Updated
-
-
song tianhui / MixFormerV2
MIT License[NeurIPS 2023] MixFormerV2: Efficient Fully Transformer Tracking
Updated -
Updated
-
Updated
-
Updated
-
Updated