423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-14 10:56:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

add adam_mini to readme

Browse Source 
Former-commit-id: e2a28f51c6
This commit is contained in:
hiyouga
2024-08-09 20:02:03 +08:00
parent 792da85866
commit 5eacd17090
12 changed files with 94 additions and 34 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/extras/llama_pro/expand.sh
View File

@@ -2,5 +2,5 @@
python scripts/llama_pro.py \
--model_name_or_path meta-llama/Meta-Llama-3-8B-Instruct \
--output_dir models/llama3-8b-instruct-pro \
--output_dir models/llama3-8b-pro \
--num_expand 8

4
examples/extras/llama_pro/llama3_freeze_sft.yaml
View File

@@ -1,5 +1,5 @@
### model
model_name_or_path: models/llama3-8b-instruct-pro
model_name_or_path: models/llama3-8b-pro
### method
stage: sft
@@ -18,7 +18,7 @@ overwrite_cache: true
preprocessing_num_workers: 16
### output
output_dir: saves/llama3-8b-instruct-pro/freeze/sft
output_dir: saves/llama3-8b-pro/freeze/sft
logging_steps: 10
save_steps: 500
plot_loss: true