Update README.md

README.md

@@ -9,12 +9,17 @@ tags:
 datasets:
 - avemio/German-RAG-HARD-REASONING-DE-THINKING
 base_model: avemio/German-RAG-R1-14B-SFT-DE-EXP
+language:
+- en
+- de
 ---
 
 # kalle07/German-RAG-R1-14B-SFT-DE-EXP-Q5_K_M-GGUF
 This model was converted to GGUF format from [`avemio/German-RAG-R1-14B-SFT-DE-EXP`](https://huggingface.co/avemio/German-RAG-R1-14B-SFT-DE-EXP) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
 Refer to the [original model card](https://huggingface.co/avemio/German-RAG-R1-14B-SFT-DE-EXP) for more details on the model.
 
+seems works good with german documents in combination with nomic embedded
+
 ## Use with llama.cpp
 Install llama.cpp through brew (works on Mac and Linux)
 
@@ -53,4 +58,4 @@ Step 3: Run inference through the main binary.
 or 
 ```
 ./llama-server --hf-repo kalle07/German-RAG-R1-14B-SFT-DE-EXP-Q5_K_M-GGUF --hf-file german-rag-r1-14b-sft-de-exp-q5_k_m.gguf -c 2048
-```
+```