Update README.md

README.md

@@ -9,11 +9,17 @@ datasets:
 - mlabonne/chatml_dpo_pairs
 ---
 
-![](https://i.imgur.com/9dhBz2j.jpg)
+![](https://i.imgur.com/CBen22L.jpg)
 
 # NeuralMarcoro14-7B
 
-This is a DPO fine-tune version of [mlabonne/Marcoro14-7B-slerp](https://huggingface.co/mlabonne/Marcoro14-7B-slerp) using the [chatml_dpo_pairs](https://huggingface.co/datasets/mlabonne/chatml_dpo_pairs) preference dataset. It improves the performance of the model on Nous benchmark suite (waiting for the results on the Open LLM Benchmark).
+This is a DPO fine-tuned version of [mlabonne/Marcoro14-7B-slerp](https://huggingface.co/mlabonne/Marcoro14-7B-slerp) using the [chatml_dpo_pairs](https://huggingface.co/datasets/mlabonne/chatml_dpo_pairs) preference dataset. It improves the performance of the model on Nous benchmark suite (waiting for the results on the Open LLM Benchmark).
+
+You can try it out in this [Space](https://huggingface.co/spaces/mlabonne/NeuralHermes-2.5-Mistral-7B-laser-GGUF-Chat) (GGUF Q4_K_M).
+
+## ⚡ Quantized models
+
+* **GGUF**: https://huggingface.co/mlabonne/NeuralMarcoro14-7B-GGUF
 
 ## 🏆 Evaluation