| license: other | |
| language: | |
| - en | |
| [EXL2](https://github.com/turboderp/exllamav2/tree/master#exllamav2) Quantization of [Putri's Megamix-A1](https://huggingface.co/gradientputri/Megamix-A1-13B). | |
| GGUF quants from [Sao10K](https://huggingface.co/Sao10K) here: [MegaMix-L2-13B-GGUF](https://huggingface.co/Sao10K/MegaMix-L2-13B-GGUF) | |
| ## Model details | |
| Quantized at 5.33bpw | |
| ## Prompt Format | |
| I'm using Alpaca format: | |
| ``` | |
| ### Instruction: | |
| ### Response: | |
| ``` |