| inference: false | |
| language: | |
| - en | |
| pipeline_tag: text-generation | |
| tags: | |
| - llama | |
| - llama-2 | |
| # Euryale-1.3-limarpv3-L2-70B-exl2 | |
| Exllama v2 quant of [Doctor-Shotgun/Euryale-1.3-limarpv3-L2-70B](https://huggingface.co/Doctor-Shotgun/Euryale-1.3-limarpv3-L2-70B) | |
| Branches: | |
| - main: measurement.json calculated at 2048 token calibration rows on PIPPA | |
| - 5.0bpw-h6: 5 decoder bits per weight, 6 head bits | |
| - ideal for 2x 24gb GPUs at 8192 context, or 1x 48gb GPU at 8192 context with CFG cache |