Closed 13416157913 closed 5 months ago
Thanks for your interest in LMFlow! We are integrating that feature right now, hopefully supporting it in 12-48 hours. Please stay tuned for our latest update 😄
Hello , Can LMFlow support Qwen1.5-1.8B model Fine-tuning?
Hi, we've tested on Qwen1.5-1.8B and the script works fine.
Please make sure you include --lora_target_modules q_proj, v_proj
(only for qwen models) in the finetune shell script:
Also, we strongly recommend you to:
cd data && ./download.sh alpaca && cd -
and specify the dataset to data/alpaca/train_conversation
, or
qwen2
for better performance.Hello , Can LMFlow support Qwen1.5-1.8B model Fine-tuning?
Hi, we've tested on Qwen1.5-1.8B and the script works fine.
Please make sure you include
--lora_target_modules q_proj, v_proj
(only for qwen models) in the finetune shell script:Also, we strongly recommend you to:
Use a conversation dataset to finetune the model. You could either:
To test the workflow, try to download a conversation dataset from out data server via:
cd data && ./download.sh alpaca && cd -
and specify the dataset to
data/alpaca/train_conversation
, or- Prepare your own conversation dataset (see here)
- Specify the conversation template to
qwen2
for better performance.
Thank you very much.
Hello , Can LMFlow support Qwen1.5-1.8B model Fine-tuning?