Update README.md

README.md

@@ -24,7 +24,7 @@ Finetuned https://huggingface.co/mesolitica/nanot5-small-malaysian-cased using 2
 - Better Cantonese translation compared to V2.
 - Better Tamil and Tanglish translation compared to V2.
 
-Wandb at https://wandb.ai/huseinzol05/nanot5-small-malaysian-cased-translation-v5-multipack-post, **still on training**.
+Wandb at https://wandb.ai/huseinzol05/nanot5-small-malaysian-cased-translation-v6-multipack-post, **still on training**.
 
 ## Public API
 
@@ -697,4 +697,5 @@ Or you can finish the PR at https://github.com/huggingface/transformers/pull/311
 
 ## how to finetune your own dataset?
 
-We finetuned using T5 SDPA multipacking forked at https://github.com/mesolitica/t5-sdpa-multipack, super undocumented, but scripts from https://github.com/huggingface/transformers/tree/main/examples/pytorch/translation should work also.
+1. We finetuned using T5 SDPA multipacking forked at https://github.com/mesolitica/t5-sdpa-multipack, super undocumented, but scripts from https://github.com/huggingface/transformers/tree/main/examples/pytorch/translation should work also.
+2. Training script at https://github.com/mesolitica/malaya/blob/master/session/translation/end-to-end/nanot5-small-multipack-compile.sh