Update README.md

README.md

@@ -55,17 +55,16 @@ Example:
 * Fine tuned on a dataset of ~1k items (Tagalog/Taglish dataset, based off Tagalog sentences augmented by LLaMA-2-13b base to create a 3-turn dialogue dataset between Human and Assistant)
 * 3/3a fine-tuned for 1/2 epochs
 * From chat LLaMA-2-7b
-* v0.3 seems to be balanced between Tagalog translation and leveraging pretrained data, more than v0.3a (which may speak more Tagalog but be less accurate or helpful); will be further curating dataset
-* Lora of [chat-tagalog v0.3 (recommended)](https://huggingface.co/922-Narra/llama-2-7b-chat-tagalog-v0.3) and [chat-tagalog v0.3](https://huggingface.co/922-Narra/llama-2-7b-chat-tagalog-v0.3a)
+* Experiment on partially synthetic data (and observing capability of LLaMA-2 base on generating Tagalog): will be further curating dataset for better attempts
+* Loras for [chat-tagalog v0.3)](https://huggingface.co/922-Narra/llama-2-7b-chat-tagalog-v0.3) and [chat-tagalog v0.3](https://huggingface.co/922-Narra/llama-2-7b-chat-tagalog-v0.3a)
 
 # llama-2-7b-tagalog-v0.3WC2 (09/01/2023)
 * Fine tuned on experimental dataset of ~6k items (Tagalog/Taglish dataset, based off Tagalog sentences and Wiki entries augmented by LLaMA-2-13b to create a dialogue-QnA dataset between Human and Assistant)
 * 1 epoch
 * From chat LLaMA-2-7b
-* Tends to fall into repetition loop
 
 # llama-2-13b-tagalog-v0.3 loras (09/01/2023)
 * Fine tuned on dataset of ~1k items (Tagalog/Taglish dataset, based off Tagalog sentences augmented by LLaMA-2-13b base to create a 3-turn dialogue dataset between Human and Assistant)
 * 3/3a fine-tuned for 1 epoch, rank = 16/8
 * From LLaMA-2-13b
-* Less helpful results than 7b (suspecting base and dataset, trying LLaMA-2-13b chat and curated dataset for next attempts)
+* Trying LLaMA-2-13b chat/other base and curated dataset for next attempts