metadata
license: other
language:
- en
ExLlamaV2 Models of Gryphe's MythoMax L2 13B.
Other quantized models are available from TheBloke: GGML - GPTQ - GGUF - AWQ
Model details
| Branch | Bits | Perplexity | Desc |
|---|---|---|---|
| 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? |
To be updated
Prompt Format
This model primarily uses Alpaca formatting, so for optimal model performance, use:
<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: