01 2024 档案

摘要：multiple GPUs in single node click to view the code torchrun --nnodes 1 --nproc_per_node 2 examples/finetuning.py --enable_fsdp --use_peft --peft_meth 阅读全文

摘要：command In these commands, I changed the prompt, input format and output format. click to view the commad # original prompt + qutsion_input + true_opt 阅读全文

摘要：using gsm8k-rft-llama7b-u13b_evaluation env: lm_evaluation llama2 7B using GSM8K-eval llama2 7B llama2 13B 阅读全文

摘要：MT bench 1 introduction We create MT-bench, a benchmark consisting of 80 high-quality multi-turn questions. MT-bench is designed to test multi-turn co 阅读全文

摘要：use code-eval command git clone https://github.com/abacaj/code-eval.git cd code-eval conda create -n human_eval python=3.10 conda activate human_eval 阅读全文

摘要：note: the datasets are classified into two types, generative(the answer is natural language, the length and content are not in a fixed format) and sel 阅读全文