Update README.md

README.md

@@ -10,10 +10,10 @@ tags:
 - trl
 base_model: SeaLLMs/SeaLLM-7B-v2
 datasets:
-- facebook/belebele
+- 922-Narra/synthetic_tagalog_test_02102024
 ---
 # AKA Tagamistral-7b-v1:
-* Yet another archived test/toy model, fine-tuned on portion of Tagalog part of belebele dataset
+* Yet another archived test/toy model from ~12/2023, fine-tuned on a synthetic Tagalog dataset partially produced by [Mistral](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)
 * Base: [SeaLLM](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2)
 * [GGUF](https://huggingface.co/922-Narra/tagalog-seallm-7b-v1)
 
@@ -41,7 +41,6 @@ This mistral model was trained 2x faster with [Unsloth](https://github.com/unslo
 ### WARNINGS AND DISCLAIMERS
 There is still a chance that the model may switch to English or Taglish.
 
-Results may improve from a cleaner and bigger portion of the belebele dataset fine-tuned on. Additionally, it is possible that the Tagalog capability still comes mostly from the fine-tuned base more than the dataset.
-
-Finally, this model is not guaranteed to output aligned or safe outputs nor is it meant for production use - use at your own risk!
+It is possible that the Tagalog capability still comes mostly from the fine-tuned base more than the dataset.
 
+Finally, this model is not guaranteed to output aligned or safe outputs nor is it meant for production use - use at your own risk!