metadata
license: other
language:
- en
EXL2 Quantization of Gryphe's MythoMax L2 13B.
Other quantized models are available from TheBloke: GGML - GPTQ - GGUF - AWQ
Model details
Base Perplexity : 5.7447
| Branch | bits | Perplexity | Description |
|---|---|---|---|
| 3bit | 3.73 | 5.8251 | Low bits quant while still good |
| 4bit | 4.33 | 5.7784 | can go 6K context on T4 GPU |
| main | 5.33 | 5.7427 | 4k Context on T4 GPU (recommended if you use Google Colab) |
| 6bit | 6.13 | 5.7347 | For those who want better quality and capable of running it |
I'll upload the 7 and 8 bits quant if someone request it. (Idk y the 5 bits quant preplexity is lower than higher bits quant, I think I did something wrong?)
Prompt Format
Alpaca format:
### Instruction:
### Response: