423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-08-22 05:32:51 +08:00
Code Issues Packages Projects Releases Wiki Activity

1. fix output_dir in llama3_lora_pretrain.yaml

Browse Source 
2. add llava1_5.yaml for inference


Former-commit-id: 982a1cdd24dfa51535af3e49c7ea80fddc95b0ee
This commit is contained in:
codingma 2024-07-13 13:16:22 +08:00
parent 0fa59c9b4c
commit 1ccc6153c7
2 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
examples/inference/llava1_5.yaml Normal file
View File

@ -0,0 +1,3 @@
model_name_or_path: llava-hf/llava-1.5-7b-hf
template: vicuna
visual_inputs: true

2
examples/train_lora/llama3_lora_pretrain.yaml
View File

@ -15,7 +15,7 @@ overwrite_cache: true
preprocessing_num_workers: 16
### output
output_dir: saves/llama3-8b/lora/sft
output_dir: saves/llama3-8b/lora/pretrain
logging_steps: 10
save_steps: 500
plot_loss: true