world2025

Results 113 comments of world2025

About jester-v1 datasets

@Lihongjian520 hello，你这个做的怎么样了，可以分享一下吗？

Code error

@zhenhao-huang 你好，请问可以分享下你能够跑通的代码吗 包括推理一张图片的demo，谢谢

predict error

@luoyexk 谢谢，请问下你这边运行成功的各个包的版本能说下吗

inference

ok, thx

weight

@ESK-01 好的，谢谢

An attempt to make LLaMA to act like ChatGPT - success! Amazing result from scratch!

great

There were missing keys in the checkpoint model loaded

@darrenwang00 你好，是在后面加一个set_peft_model_state_dict(model, state_dict)这个吗

微调完之后的两个文件只有4kb

@yuanzhiyong1999 https://github.com/tloen/alpaca-lora/issues/334

Merging LoRA weights into a quantized model is not supported 嗯。你说的

但是qlora训练只能单卡

[Question] Can curve-based enhancing method handle over-exposure images correction?

@CaptainEven @Li-Chongyi @gwp2021 hello,do you have train model use over-exposure data ?