Update README.md

README.md

@@ -37,15 +37,15 @@ Check the examples in the evaluation section to get an idea of its performance.
 
 ## ⚡ Quantized models
 
-Thanks to [Eric Hartford](https://huggingface.co/ehartford), [elinas](https://huggingface.co/elinas), and the [mlx-community](https://huggingface.co/mlx-community) for providing these models.
+Thanks to [Bartowski](https://huggingface.co/ehartford), [elinas](https://huggingface.co/elinas), the [mlx-community](https://huggingface.co/mlx-community) and others for providing these models.
 
-* **GGUF**: https://huggingface.co/cognitivecomputations/Meta-Llama-3-120B-Instruct-gguf
+* **GGUF**: https://huggingface.co/lmstudio-community/Meta-Llama-3-120B-Instruct-GGUF
 * **EXL2**: https://huggingface.co/elinas/Meta-Llama-3-120B-Instruct-4.0bpw-exl2
 * **mlx**: https://huggingface.co/mlx-community/Meta-Llama-3-120B-Instruct-4bit
 
 ## 🏆 Evaluation
 
-This model is great for creative writing but struggles in other tasks. I'd say use it with caution and don't expect it to outperform GPT-4 outside of some specific use cases.
+This model is great for creative writing but struggles in other tasks. I'd say use it with caution and don't expect it to outperform GPT-4 outside of some very specific use cases.
 
 * **X thread by Eric Hartford (creative writing)**: https://twitter.com/erhartford/status/1787050962114207886
 * **X thread by Daniel Kaiser (creative writing)**: https://twitter.com/spectate_or/status/1787257261309518101