Update README.md

README.md

@@ -1,11 +1,11 @@
----
-title: README
-emoji: 🔥
-colorFrom: purple
-colorTo: purple
-sdk: static
-pinned: true
----
+---
+title: README
+emoji: 🔥
+colorFrom: purple
+colorTo: purple
+sdk: static
+pinned: true
+---
 
 These are my own quantizations (updated almost daily).  
 The difference with normal quantizations is that I quantize the output and embed tensors to f16.  
@@ -14,7 +14,8 @@ This creates models that are little or not degraded at all and have a smaller si
 They run at about 3-6 t/sec on CPU only using llama.cpp  
 And obviously faster on computers with potent GPUs   
 
-
+* [ZeroWw/Llama-3-8B-Instruct-Gradient-1048k-GGUF](https://huggingface.co/ZeroWw/Llama-3-8B-Instruct-Gradient-1048k-GGUF)
+* [ZeroWw/Pythia-Chat-Base-7B-GGUF](https://huggingface.co/ZeroWw/Pythia-Chat-Base-7B-GGUF)
 * [ZeroWw/Yi-1.5-6B-Chat-GGUF](https://huggingface.co/ZeroWw/Yi-1.5-6B-Chat-GGUF)
 * [ZeroWw/DeepSeek-Coder-V2-Lite-Base-GGUF](https://huggingface.co/ZeroWw/DeepSeek-Coder-V2-Lite-Base-GGUF)
 * [ZeroWw/Yi-1.5-9B-32K-GGUF](https://huggingface.co/ZeroWw/Yi-1.5-9B-32K-GGUF)