Update README.md

README.md

@@ -2,14 +2,12 @@
 license: apache-2.0
 inference: false
 ---
-![perplexity stats](https://huggingface.co/eachadea/ggml-vicuna-13b-1.1/resolve/main/perplexity.png)
 
 **NOTE: This GGML conversion is primarily for use with llama.cpp.**  
 - 13B parameters
 - 4-bit quantized
 - Based on version 1.1
-- Used PR "More accurate Q4_0 and Q4_1 quantizations #896" (should be closer in quality to unquantized)
-- For q4_2, "Q4_2 ARM #1046" was used. Will update regularly if new changes are made.
+- Used best available quantization for each format
 - **Choosing between q4_0, q4_1, and q4_2:**
   - 4_0 is the fastest. The quality is the poorest.
   - 4_1 is slower. The quality is noticeably better.