--- base_model: Delta-Vector/Austral-70B-Preview base_model_relation: quantized quantized_by: ArtusDev license: llama3.3 language: - en library_name: transformers datasets: - PocketDoc/Dans-Personamaxx-VN - NewEden/LIMARP-Complexity - NewEden/PIPPA-Mega-Filtered - NewEden/OpenCAI-ShareGPT - NewEden/Creative_Writing-Complexity - NewEden/Light-Novels-Roleplay-Logs-Books-Oh-My-duplicate-turns-removed - PocketDoc/Dans-Failuremaxx-Adventure-3 - NewEden/Books-V2-ShareGPT - NewEden/Deepseek-V3-RP-Filtered - NewEden/BlueSky-10K-Complexity - NewEden/Final-Alpindale-LNs-ShareGPT - NewEden/DeepseekRP-Filtered - NewEden/RP-logs-V2-Experimental - anthracite-org/kalo_opus_misc_240827 - anthracite-org/kalo_misc_part2 - NewEden/vanilla-backrooms-claude-sharegpt - NewEden/Storium-Prefixed-Clean tags: - roleplay - finetune - axolotl - creative-writing - 70B - llama - exl3 --- ## EXL3 Quants of Delta-Vector/Austral-70B-Preview EXL3 quants of [Delta-Vector/Austral-70B-Preview](https://huggingface.co/Delta-Vector/Austral-70B-Preview) using exllamav3 for quantization. ### Quants | Quant(Revision) | Bits per Weight | Head Bits | | -------- | ---------- | --------- | | [2.5_H6](https://huggingface.co/ArtusDev/Delta-Vector_Austral-70B-Preview-EXL3/tree/2.5bpw_H6) | 2.5 | 6 | | [3.0_H6](https://huggingface.co/ArtusDev/Delta-Vector_Austral-70B-Preview-EXL3/tree/3.0bpw_H6) | 3.0 | 6 | | [3.25_H6](https://huggingface.co/ArtusDev/Delta-Vector_Austral-70B-Preview-EXL3/tree/3.25bpw_H6) | 3.25 | 6 | | [3.5_H6](https://huggingface.co/ArtusDev/Delta-Vector_Austral-70B-Preview-EXL3/tree/3.5bpw_H6) | 3.5 | 6 | | [4.0_H6](https://huggingface.co/ArtusDev/Delta-Vector_Austral-70B-Preview-EXL3/tree/4.0bpw_H6) | 4.0 | 6 | | [4.25_H6](https://huggingface.co/ArtusDev/Delta-Vector_Austral-70B-Preview-EXL3/tree/4.25bpw_H6) | 4.25 | 6 | | [4.5_H6](https://huggingface.co/ArtusDev/Delta-Vector_Austral-70B-Preview-EXL3/tree/4.5bpw_H6) | 4.5 | 6 | | [5.0_H6](https://huggingface.co/ArtusDev/Delta-Vector_Austral-70B-Preview-EXL3/tree/5.0bpw_H6) | 5.0 | 6 | | [6.0_H6](https://huggingface.co/ArtusDev/Delta-Vector_Austral-70B-Preview-EXL3/tree/6.0bpw_H6) | 6.0 | 6 | | [8.0_H6](https://huggingface.co/ArtusDev/Delta-Vector_Austral-70B-Preview-EXL3/tree/8.0bpw_H6) | 8.0 | 6 | | [8.0_H8](https://huggingface.co/ArtusDev/Delta-Vector_Austral-70B-Preview-EXL3/tree/8.0bpw_H8) | 8.0 | 8 | ### Downloading quants with huggingface-cli
Click to view download instructions Install hugginface-cli: ```bash pip install -U "huggingface_hub[cli]" ``` Download quant by targeting the specific quant revision (branch): ``` huggingface-cli download ArtusDev/Delta-Vector_Austral-70B-Preview-EXL3 --revision "5bpw_H6" --local-dir ./ ```