terminator123

Results 19 comments of terminator123

Model do not adapt to my dataset after finetuning

have u solved the problem? i have the same problem

Training model save problem

i met the same problem too

mmi_model缺少config文件，作者能不能补一下

> 你找到了吗，同求

MMI_MODEL缺少config.json

> 你找到了吗，通求

about finetune_task_lora.sh

> I had this issue where finetune_task_lora.sh doesn't create mm_projector.bin which also limited my usage of the finetuned_lora model. (I cannot merge or use it for inference). I changed extract_mm_projector...

[Usage] LoRA finetuned weights provided for vicuna-13b-v1.3 gives NaN / inf error when performing inference on COCO-2014 questions after merging LoRA weights

how did you download the dataset coco/coco_dataset/val2014?

请教下有gpt2的微调的相关文档么？

请问你解决了吗

NCCL communicator error: Socket Timeout when finetuning 70B model on 2 * (8* A100(80G))

> set "CUDA_DEVICE_MAX_CONNECTIONS" to 32 maybe you need in environment. pls have a try @yguo33 @gonggaohan @tginart RuntimeError: Using sequence parallelism requires setting the environment variable CUDA_DEVICE_MAX_CONNECTIONS to 1, when...

Is there a first pretraining stage model for Llama 7b?

i have the same question, have u resolved it ?