Update README.md

README.md

@@ -10,6 +10,9 @@ tags:
 - llama-2
 - german
 - deutsch
+datasets:
+- Christoph911/German-legal-SQuAD
+- philschmid/test_german_squad
 ---
 
 # Llama 2 13b Chat German
@@ -26,7 +29,12 @@ I am working on improving the model´s capabilities and will update the model if
 A quantized GGML version for use with llama.cpp, kobold.cpp and other GUIs for CPU inference can be found [here](https://huggingface.co/jphme/Llama-2-13b-chat-german-GGML).
 
 Please note the license of the base model, which is contained in the repo under LICENSE.TXT and see the original model card below for more information.
- 
+
+## Data
+
+* Prorietary German Conversation Dataset 
+* German SQuAD and German legal SQuAD data (see datasets), augmented with "wrong" contexts, to improve factual RAG
+
 ## Prompt Template
 
 Llama2 Chat uses a new prompt format:
@@ -176,4 +184,4 @@ Please report any software “bug,” or other problems with the models through
 |---|---|---|---|---|
 |7B| [Link](https://huggingface.co/llamaste/Llama-2-7b) | [Link](https://huggingface.co/llamaste/Llama-2-7b-hf) | [Link](https://huggingface.co/llamaste/Llama-2-7b-chat) | [Link](https://huggingface.co/llamaste/Llama-2-7b-chat-hf)|
 |13B| [Link](https://huggingface.co/llamaste/Llama-2-13b) | [Link](https://huggingface.co/llamaste/Llama-2-13b-hf) | [Link](https://huggingface.co/llamaste/Llama-2-13b-chat) | [Link](https://huggingface.co/llamaste/Llama-2-13b-hf)|
-|70B| [Link](https://huggingface.co/llamaste/Llama-2-70b) | [Link](https://huggingface.co/llamaste/Llama-2-70b-hf) | [Link](https://huggingface.co/llamaste/Llama-2-70b-chat) | [Link](https://huggingface.co/llamaste/Llama-2-70b-hf)|
+|70B| [Link](https://huggingface.co/llamaste/Llama-2-70b) | [Link](https://huggingface.co/llamaste/Llama-2-70b-hf) | [Link](https://huggingface.co/llamaste/Llama-2-70b-chat) | [Link](https://huggingface.co/llamaste/Llama-2-70b-hf)|