Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

在单机多卡训练过程结束后,当尝试加载模型以进行对话交互时,模型的响应出现了乱码现象。 #3733

Closed
1 task done
lollipopyu opened this issue May 14, 2024 · 0 comments
Labels
wontfix This will not be worked on

Comments

@lollipopyu
Copy link

Reminder

  • I have read the README and searched the existing issues.

Reproduction

CUDA_VISIBLE_DEVICES=0,1 llamafactory-cli train --stage sft --do_train True --model_name_or_path ./Qwen-1_8B-Chat --finetuning_type lora --quantization_bit 4 --template qwen --flash_attn auto --dataset_dir data --dataset self_coganition --cutoff_len 1024 --learning_rate 0.0002 --num_train_epochs 3.0 --max_samples 1000 --per_device_train_batch_size 2 --gradient_accumulation_steps 8 --lr_scheduler_type cosine --max_grad_norm 1.0 --logging_steps 5 --save_steps 100 --warmup_steps 0 --optim adamw_torch --packing False --report_to none --output_dir saves/Qwen-1.8B-Chat/lora/train_2024-05-13-18-20-06 --fp16 True --lora_rank 8 --lora_alpha 16 --lora_dropout 0.1 --lora_target c_attn --plot_loss True

Expected behavior

训练正常结束,但加载模型之后,与之对话,出现乱码。
企业微信截图_17155962283403

System Info

No response

Others

No response

@hiyouga hiyouga added the pending This problem is yet to be addressed. label May 14, 2024
@hiyouga hiyouga added wontfix This will not be worked on and removed pending This problem is yet to be addressed. labels May 29, 2024
@hiyouga hiyouga closed this as not planned Won't fix, can't repro, duplicate, stale May 29, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
wontfix This will not be worked on
Projects
None yet
Development

No branches or pull requests

2 participants