Update README.md

README.md

@@ -9,25 +9,21 @@ Other quantized models are available from TheBloke: [GGML](https://huggingface.c
 
 ## Model details
 
-| **Branch**                                                           | **Bits** | **Perplexity** | **Desc**                                     |
-|----------------------------------------------------------------------|----------|----------------|----------------------------------------------|
-| [main](https://huggingface.co/R136a1/MythoMax-L2-13B-exl2/tree/main) | 5        | idk, forgot    | Idk why I made this, 1st try                 |
-|                                                                      | 4        |                |                                              |
-|                                                                      | 6.5      | 6.1074         | Can run 4096 context size (tokens) on T4 GPU |
-|                                                                      | 7        | 6.1056         | 2048 max context size for T4 GPU             |
-|                                                                      | 8        | 6.1027         | Just, why?                                   |
+| **Branch**                                                           | **Bits** | **Perplexity** |
+|----------------------------------------------------------------------|----------|----------------|
+| [main](https://huggingface.co/R136a1/MythoMax-L2-13B-exl2/tree/main) | 5        | 6.1018         |
+| [6bit](https://huggingface.co/R136a1/MythoMax-L2-13B-exl2/tree/6bit) | 6        | 6.1182         |
+| -                                                                    | 7        | 6.1056         |
+| -                                                                    | 8        | 6.1027         |
 
-To be updated
+I'll upload the 7 and 8 bits quant if someone request it.
 
 ## Prompt Format
 
-This model primarily uses Alpaca formatting, so for optimal model performance, use:
+Alpaca format:
 ```
-<System prompt/Character Card>
-
 ### Instruction:
-Your instruction or question here.
-For roleplay purposes, I suggest the following - Write <CHAR NAME>'s next reply in a chat between <YOUR NAME> and <CHAR NAME>. Write a single reply only.
+
 
 ### Response:
 ```