---
base_model: Delta-Vector/Francois-PE-V2-Huali-12B
base_model_relation: quantized
quantized_by: ArtusDev
library_name: transformers
tags:
- fine-tuning
- prose
- KTO
- axolotl
- finetune
- roleplaying
- creative-writing
- exl3
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
- NewEden/KTO-IF-Dans
- NewEden/KTO-Instruct-Mix
- NewEden/Opus-accepted-hermes-rejected-shuffled
---

## EXL3 Quants of Delta-Vector/Francois-PE-V2-Huali-12B

EXL3 quants of [Delta-Vector/Francois-PE-V2-Huali-12B](https://huggingface.co/Delta-Vector/Francois-PE-V2-Huali-12B) using <a href="https://github.com/turboderp-org/exllamav3/">exllamav3</a> for quantization.

### Quants
| Quant(Revision) | Bits per Weight | Head Bits |
| -------- | ---------- | --------- |
| [2.5_H6](https://huggingface.co/ArtusDev/Delta-Vector_Francois-PE-V2-Huali-12B-EXL3/tree/2.5bpw_H6) | 2.5 | 6 |
| [3.0_H6](https://huggingface.co/ArtusDev/Delta-Vector_Francois-PE-V2-Huali-12B-EXL3/tree/3.0bpw_H6) | 3.0 | 6 |
| [3.5_H6](https://huggingface.co/ArtusDev/Delta-Vector_Francois-PE-V2-Huali-12B-EXL3/tree/3.5bpw_H6) | 3.5 | 6 |
| [4.0_H6](https://huggingface.co/ArtusDev/Delta-Vector_Francois-PE-V2-Huali-12B-EXL3/tree/4.0bpw_H6) | 4.0 | 6 |
| [4.5_H6](https://huggingface.co/ArtusDev/Delta-Vector_Francois-PE-V2-Huali-12B-EXL3/tree/4.5bpw_H6) | 4.5 | 6 |
| [5.0_H6](https://huggingface.co/ArtusDev/Delta-Vector_Francois-PE-V2-Huali-12B-EXL3/tree/5.0bpw_H6) | 5.0 | 6 |
| [6.0_H6](https://huggingface.co/ArtusDev/Delta-Vector_Francois-PE-V2-Huali-12B-EXL3/tree/6.0bpw_H6) | 6.0 | 6 |
| [8.0_H8](https://huggingface.co/ArtusDev/Delta-Vector_Francois-PE-V2-Huali-12B-EXL3/tree/8.0bpw_H8) | 8.0 | 8 |

### Downloading quants with huggingface-cli

<details>
  <summary>Click to view download instructions</summary>

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_Francois-PE-V2-Huali-12B-EXL3 --revision "5.0bpw_H6" --local-dir ./
```
</details>