| license: other | |
| 5 bit quantization of airoboros 70b 1.4.1 (https://huggingface.co/jondurbin/airoboros-l2-70b-gpt4-1.4.1), using exllama2. | |
| Update 21/09/23 | |
| Re-quanted with latest exllamav2 version, which fixed some measurement issues. | |
| Also, now 5bpw works on 2x24GB VRAM cards, using gpu_split 21,21 and flash-attn (only Linux for now), for 4096 context and 1 GB to spare, to try for more. |