mengyi yan

would it be possible to share the pretrained model weights or pre-training corpus?

2

Thanks for sharing the code, however I notice that in pretrain.config, the file path leads to data/all, however there is no such folder or corpus data for pre-training, which leads...

Can mergekit be applied to merge multiple LoRA checkpoints by weights?

3

Many thanks for the great work. Can mergekit merge multiple LoRA checkpoints by provided weights, which are trained on the same base model, and output a merged LoRA weights? Peft...

Merge multiple LoRA by weights

1

### Reminder - [X] I have read the README and searched the existing issues. ### Reproduction Thanks for the great work. When merging the LoRA to base model by python...

Issues about Applying Delta

1

Thanks for your great work. However, when checking your huggingface page https://huggingface.co/YuxinJiang/Lion, I found your delta weights size is 25G, which is typically the size of LLAMA-13B model(same as vicuna-13b-delta-v1.1),...

reward model中没有任何参数来自定义数据集，可以提供一个修改方案，类似于sft model训练中的--data_path来自定义一个json文件作为reward model的训练数据吗？ 另，这个项目是不是已经不再计划维护下去了？本月的若干issue都没有回复

Supporting local LLM api server and vLLM

3

Thanks for your great work! Since https://github.com/lm-sys/FastChat can initiate a local server on llama2/vicuna, which api is quite similar to openai, it is possible to support FastChat api server, so...