Update README.md

README.md

@@ -1,7 +1,7 @@
 ---
 language:
 - en
-license: apache-2.0
+- da
 tags:
 - text-generation-inference
 - transformers
@@ -9,7 +9,20 @@ tags:
 - mistral
 - trl
 base_model: mistralai/Mistral-7B-v0.1
+datasets:
+- oscar
 ---
+<img src="https://huggingface.co/Mabeck/Heidrun-Mistral-7B-chat/resolve/main/heidrun.jpeg" alt="Heidrun Logo" width="400">
+
+# Model description
+
+Heidrun-Mistral-7B-base is a generative text model based on [Mistral-7B](https://huggingface.co/mistralai/Mistral-7B-v0.1). It has been further pretrained on a subset of the Danish corpus from [Oscar](https://huggingface.co/datasets/oscar).
+
+The dataset was first cleaned to remove most inappropriate texts. Please note that Oscar contains explicit content, and not all may have been removed.
+The model was mainly trained on shorter sentences (<3000 words).
+
+For inference or chatting please check out [Heidrun-Mistral-7B-chat](https://huggingface.co/Mabeck/Heidrun-Mistral-7B-chat).
+
 
 # Uploaded  model
 
@@ -19,4 +32,4 @@ base_model: mistralai/Mistral-7B-v0.1
 
 This mistral 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)
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)