Update README.md

README.md

@@ -6,7 +6,14 @@ tags:
 
 # Model Card for Model ID
 
-<!-- Provide a quick summary of what the model is/does. -->
+## Model
+The base model used is the Meta Llama 13B model ([meta-llama/Llama-2-13b-hf](https://huggingface.co/meta-llama/Llama-2-13b-hf)).
+## Data
+A dataset of prompt/response pairs about radiation protection, radiation physics, radiation biology and radiological technology as the apply in dental clinics was used to fine-tune the model. The dataset is in Norwegian and the model is fine-tuned to answer in Norwegian.
+## Training
+The model was trained on 6.2k prompt/response pairs from the dataset [meta-llama/Llama-2-13b-hf](https://huggingface.co/datasets/geraldOslo/RadProtDataSet) for 6 epochs on a Google Colag notebook with an A100 GPU.
+
+The [Unsloth library](https://github.com/unslothai/unsloth) was used to train the model on a single A100 GPU.
 
 
 
@@ -18,9 +25,9 @@ tags:
 
 This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
 
-- **Developed by:** [More Information Needed]
+- **Developed by:** Gerald Torgersen
 
-- **Model type:** Llama 2 13B fine-tuned
+- **Model type:** Chat model fine-tuned
 - **Language(s) (NLP):** Norwegian
 - **License:** [More Information Needed]
 - **Finetuned from model [meta-llama/Llama-2-13b-hf]:**