Search Results - RepositoryStats

2 results found Sort:

apache-2.0

Train llm (bloom, llama, baichuan2-7b, chatglm3-6b) with deepspeed pipeline mode. Faster than zero/zero++/fsdp.

llm nlp bloom llama2 pytorch pipeline deepspeed chatglm3-6b baichuan2-7b mixtral-8x7b full-finetune flash-attention model-parallization

Created 2023-06-24

27 commits to master branch, last one 10 months ago

apache-2.0

[ACL 2024 Main] NewsBench: A Systematic Evaluation Framework for Assessing Editorial Capabilities of Large Language Models in Chinese Journalism

llm gpt4 xverse acl2024 aquila2 chatgpt dataset qwen-14b baichaun2 benchmark ernie-bot framework evaluation gpt35turbo chatglm2-6b chatglm3-6b internlm-20b large-language-models

Created 2024-03-08

16 commits to hsb branch, last one 6 months ago