Update README.md

README.md

@@ -6,12 +6,11 @@ tags:
 - llama-factory
 - lora
 datasets:
-
   - Nekochu/novel17_train_alpaca_format
+  - bofenghuang/vigogne
   - jpacifico/French-Alpaca-dataset-Instruct-110K
   - MaziyarPanahi/french_instruct_human_sharegpt
-  - bofenghuang/vigogne
-  - Nekochu/Luminia-mixture
+  - Snit/french-conversation
   
 language:
   - fr
@@ -19,7 +18,7 @@ language:
 ---
 
 - Similar to the old [Nekochu/Llama-2-13B-fp16-french](https://huggingface.co/Nekochu/Llama-2-13B-fp16-french) with additional datasets.
-- I've (alway) kept LoRA `QLoRA_french_sft` so it can be applied to any LLaMA-3.1-8B fine-tuned model. It may affect performance.
+- I've (alway) kept LoRA `QLoRA_french_sft` so it can be applied to any *LLaMA-3.1-8B* fine-tuned model but may affect performance.
 
 <details>
   <summary>This training can be replicated using LLaMA-Factory. </summary>