Update README.md

README.md

@@ -1,22 +1,18 @@
 ---
 language:
 - en
+- ja
 license: apache-2.0
 tags:
-- text-generation-inference
-- transformers
-- unsloth
 - llama
-- trl
 base_model: NilanE/tinyllama-relora-merge
+datasets:
+- NilanE/ParallelFiction-Ja_En-100k
 ---
 
-# Uploaded  model
+Trained for 2 epochs on NilanE/ParallelFiction-Ja_En-100k using QLoRA. CPO tune is in-progress. 
 
-- **Developed by:** NilanE
-- **License:** apache-2.0
-- **Finetuned from model :** NilanE/tinyllama-relora-merge
+Input should be 500-1000 tokens long. Make sure to set 'do_sample = False' if using HF transformers for inference, or otherwise set temperature to 0 for deterministic outputs.
 
-This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
-
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+## Prompt format
+"""Translate this from Japanese to English:\n### JAPANESE:\n{source_text}\n### ENGLISH:\n"""