Update README.md
Browse files
README.md
CHANGED
|
@@ -9,6 +9,14 @@ Other quantized models are available from TheBloke: [GGML](https://huggingface.c
|
|
| 9 |
|
| 10 |
## Model details
|
| 11 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
To be updated
|
| 13 |
|
| 14 |
## Prompt Format
|
|
|
|
| 9 |
|
| 10 |
## Model details
|
| 11 |
|
| 12 |
+
| Branch | Bits | Perplexity | Desc |
|
| 13 |
+
|:--------------------------------------------------------------------:|:----:|:-----------:|:--------------------------------------------:|
|
| 14 |
+
| [main](https://huggingface.co/R136a1/MythoMax-L2-13B-exl2/tree/main) | 5 | idk, forgot | Idk why I made this, 1st try |
|
| 15 |
+
| | 4 | | |
|
| 16 |
+
| | 6.5 | 6.1074 | Can run 4096 context size (tokens) on T4 GPU |
|
| 17 |
+
| | 7 | 6.1056 | 2048 max context size for T4 GPU |
|
| 18 |
+
| | 8 | 6.1027 | Just, why? |
|
| 19 |
+
|
| 20 |
To be updated
|
| 21 |
|
| 22 |
## Prompt Format
|