1SingleFeng comments

Results 30 comments of


                                            1SingleFeng

关于微调

> 看了下直播回放，内容还是在讲纯技术实现，即类似lora的原理；请问是否可以在readme放出微调应用示例呢？或是给个参考之类的请问有直播回放吗

Export model by using Aimet for AI stack stable diffusion demo

> anyone has any comments, i think this should be a torch & AimetCommon version compatible issue Could you please tell me how to check the corresponding torch version of...

Inquiry about Minimum GPU Requirements

Hello, from my understanding, this project requires a GPU Compute Capacity higher than 8.0, but the RTX 2080Ti is only 7.5 (find on https://developer.nvidia.com/cuda-gpus). You can use AutoAWQ (https://github.com/casper-hansen/AutoAWQ), which...

使用zero3进行多机多卡全量微调，保存的模型权重不完整

> 按照model.safetensors.index.json，模型权重分为了model-00001-of-00004.safetensors，model-00002-of-00004.safetensors， model-00003-of-00004.safetensors， model-00004-of-00004.safetensors进行保存，但是实际上只有三个模型权重文件，没有model-00001-of-00004.safetensors 您好，zero3可以跑多机多卡吗

MiniCPM-Llama3-V 2.5 int4 版本支持微调吗？

> Another question, can you guys (i mean authors) share the quantize scripts? we need the script after sft this model. > Another question, can you guys (i mean authors)...

[BUG] 如何合并lora后的权重

> https://github.com/OpenBMB/MiniCPM-V/tree/main/finetune#lora-finetuning 这个多卡运行不了，报错： Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cuda:6! (when checking argument for argument src in method wrapper_CUDA_scatter__src)...