---
license: cc-by-nc-4.0
base_model_relation: quantized
quantized_by: Quant-Cartel
base_model: rAIfle/Acolyte-22B

---
```
  e88 88e                               d8     
 d888 888b  8888 8888  ,"Y88b 888 8e   d88     
C8888 8888D 8888 8888 "8" 888 888 88b d88888   
 Y888 888P  Y888 888P ,ee 888 888 888  888     
  "88 88"    "88 88"  "88 888 888 888  888     
      b                                        
      8b,                                      
 
  e88'Y88                  d8           888    
 d888  'Y  ,"Y88b 888,8,  d88    ,e e,  888    
C8888     "8" 888 888 "  d88888 d88 88b 888    
 Y888  ,d ,ee 888 888     888   888   , 888    
  "88,d88 "88 888 888     888    "YeeP" 888    
                                               
PROUDLY PRESENTS         
```
# Acolyte-22B-exl2-longcal

Quantized using 115 rows of 8192 tokens from the default ExLlamav2-calibration dataset.

Branches:
- `main` -- `measurement.json`
- 8b8h -- 8bpw, 8bit lm_head
- 4.63b6h -- 4.63bpw, 6bit lm_head
- 3.09b6h -- 3.09bpw, 6bit lm_head
- 2.32b6h -- 2.32bpw, 6bit lm_head

Original model link: [rAIfle/Acolyte-22B](https://huggingface.co/rAIfle/Acolyte-22B)

Original model README below.

-----
# Acolyte-22B

![image/png](https://cdn-uploads.huggingface.co/production/uploads/6569a4ed2419be6072890cf8/3dcGMcrWK2-2vQh9QBt3o.png)

LoRA of a bunch of random datasets on top of Mistral-Small-Instruct-2409, then SLERPed onto base at 0.5. Decent enough for its size.
Check the [LoRA](https://huggingface.co/rAIfle/Acolyte-LORA) for dataset info.

Use `Mistral V2 & V3` template.