Update README.md

README.md

@@ -1,7 +1,7 @@
 ---
 base_model: mistralai/Mistral-7B-Instruct-v0.3
 datasets:
-- generator
+- naimsassine/belgian-law-qafrench-dataset
 library_name: peft
 license: apache-2.0
 tags:
@@ -18,21 +18,25 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mistralinstruct-7b-sft-lora
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on the generator dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on the Belgian Law QnA dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.2937
 
 ## Model description
 
-More information needed
+The goal of this model was to experiment how far we can push a model by fine tuning it on a french QnA dataset on Belgian Law. The goal here is to see if we can get a small
+size LLM to become good enough in terms of Legal Expertise in a specific country
 
 ## Intended uses & limitations
 
-More information needed
+Legal Question Answering (Belgian Law/French)
 
 ## Training and evaluation data
 
-More information needed
+SFT-LORA
+Big thanks to Niels Rogge's notebook that helped me through the process 
+https://github.com/NielsRogge/Transformers-Tutorials/blob/master/Mistral/Supervised_fine_tuning_(SFT)_of_an_LLM_using_Hugging_Face_tooling.ipynb
+
 
 ## Training procedure